feat(exec): log per-attempt chain verdicts for pass rate visibility

DECISIONS.md

@@ -44,6 +44,29 @@ Record *why* things are the way they are. Future-you will thank present-you.
 
 **Consequences**: More operational complexity than Chroma, but isolation is non-negotiable for client work.
 
+## 2026-04-22 — Hyperguild scope reset: drop parametric learning, simplify brain
+
+**Context**: After shipping Phases 1–4 (MCP server, 6 skills, model orchestration, session logging, CD pipeline), we critically reviewed what was theater vs genuinely useful.
+
+**Decisions**:
+
+1. **Drop the parametric learning pipeline.** SFT/DPO/RL extraction, `brain/training-data/` directory structure, Axolotl/LLaMA-Factory fine-tuning loop — all cut. The loop requires thousands of high-quality examples to move the needle, which a solo consultant won't generate. Better base models ship faster than any fine-tuning effort could keep up with. This is a research project, not a productivity tool.
+
+2. **Simplify the brain to plain markdown.** `brain/knowledge/` replaces `brain/wiki/ + brain/raw/ + brain/training-data/`. The trainer and retrospective workers write markdown entries. `brain_query` searches markdown. No ingestion pipeline, no tagging for significance review, no structured JSONL formats.
+
+3. **Measure the escalation chain before assuming it's useful.** Local model (phi4) only belongs in a skill's chain if it passes Claude verification at a meaningful rate. Where it fails >70% of the time, it adds cost not value. Per-skill hit rate logging is the prerequisite to honest chain configuration.
+
+4. **Keep what's real**: MCP tool surface, session logging with attempt records, tier detection, CD pipeline, bridge to Claude Code.
+
+**What to build next** (in priority order):
+- `brain_query` injection into skill handlers before spawning workers — this makes the declarative brain actually function
+- `protocols.md` — behavioral contract injected into every worker prompt
+- Per-skill pass rate logging and chain tuning
+
+**Consequences**: Simpler system with a shorter feedback loop. The brain becomes real only when skill handlers query it. Training data ambitions deferred indefinitely — revisit if local model capabilities improve enough that fine-tuning becomes worthwhile.
+
+---
+
 ## 2026-04-08 — Mistral Vibe gets its own adapter
 
 **Context**: Vibe doesn't read `AGENTS.md` — it uses `~/.vibe/prompts/` and `~/.vibe/agents/` with TOML config.

cmd/supervisor/main.go

@@ -43,6 +43,17 @@ func main() {
 		os.Exit(1)
 	}
 
+	protocolsPrompt, err := os.ReadFile(cfg.ConfigDir + "/protocols.md")
+	if err != nil {
+		logger.Error("read protocols.md", "path", cfg.ConfigDir+"/protocols.md", "err", err)
+		os.Exit(1)
+	}
+
+	// prependProtocols prepends the shared protocols to a skill discipline file.
+	prependProtocols := func(skillPrompt []byte) string {
+		return string(protocolsPrompt) + "\n---\n\n" + string(skillPrompt)
+	}
+
 	tddPrompt, err := os.ReadFile(cfg.ConfigDir + "/tdd.md")
 	if err != nil {
 		logger.Error("read tdd.md", "path", cfg.ConfigDir+"/tdd.md", "err", err)
@@ -103,6 +114,18 @@ func main() {
 			orch := iexec.NewOrchestrator(chain, litellmExec.Run, claudeExec.Run, verifier, models.LlamaSwapURL(), &attempts)
 			result, err := orch.Run(ctx, req)
 			result.Attempts = attempts // attach orchestration metadata before returning
+			// Log per-attempt verdicts so pass rates are visible in pod logs.
+			for i, a := range attempts {
+				logger.Info("chain attempt",
+					"skill", skill,
+					"attempt", i+1,
+					"model", a.Model,
+					"tier", a.Tier,
+					"verdict", a.Verdict,
+					"duration_ms", a.DurationMs,
+					"warm", a.WarmStart,
+				)
+			}
 			return result, err
 		}
 	}
@@ -114,10 +137,11 @@ func main() {
 	reg := registry.New()
 	reg.Register(tdd.New(tdd.Config{
 		SystemPrompt:  string(systemPrompt),
-		SkillPrompt:  string(tddPrompt),
+		SkillPrompt:   prependProtocols(tddPrompt),
 		DefaultModel:  models.ChainFor("tdd", "")[0],
 		ExecutorFn:    buildOrch("tdd"),
 		SessionsDir:   cfg.SessionsDir,
+		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(brain.New(brain.Config{
 		IngestBaseURL: cfg.IngestBaseURL,
@@ -129,32 +153,35 @@ func main() {
 		SessionsDir: cfg.SessionsDir,
 	}))
 	reg.Register(retrospective.New(retrospective.Config{
-		SkillPrompt:  string(retroPrompt),
+		SkillPrompt:  prependProtocols(retroPrompt),
 		DefaultModel: models.ChainFor("retrospective", "")[0],
 		SessionsDir:  cfg.SessionsDir,
 		ExecutorFn:   buildOrch("retrospective"),
 	}))
 	reg.Register(review.New(review.Config{
-		SkillPrompt:  string(reviewPrompt),
+		SkillPrompt:   prependProtocols(reviewPrompt),
 		DefaultModel:  models.ChainFor("review", "")[0],
 		ExecutorFn:    buildOrch("review"),
 		SessionsDir:   cfg.SessionsDir,
+		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(skilldebug.New(skilldebug.Config{
-		SkillPrompt:  string(debugPrompt),
+		SkillPrompt:   prependProtocols(debugPrompt),
 		DefaultModel:  models.ChainFor("debug", "")[0],
 		ExecutorFn:    buildOrch("debug"),
 		SessionsDir:   cfg.SessionsDir,
+		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(spec.New(spec.Config{
-		SkillPrompt:  string(specPrompt),
+		SkillPrompt:   prependProtocols(specPrompt),
 		DefaultModel:  models.ChainFor("spec", "")[0],
 		ExecutorFn:    buildOrch("spec"),
 		SessionsDir:   cfg.SessionsDir,
+		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(trainer.New(trainer.Config{
-		ReaderPrompt: string(trainerReaderPrompt),
-		WriterPrompt: string(trainerWriterPrompt),
+		ReaderPrompt: prependProtocols(trainerReaderPrompt),
+		WriterPrompt: prependProtocols(trainerWriterPrompt),
 		DefaultModel: models.ChainFor("trainer", "")[0],
 		ExecutorFn:   buildOrch("trainer"),
 		SessionsDir:  cfg.SessionsDir,

config/supervisor/protocols.md

@@ -1,27 +1,55 @@
-# The Hyperguild Way
+# The Hyperguild Way — Worker Protocols
 
-These protocols are injected into every worker invocation. They define how you behave as a member of the hyperguild.
+Injected into every worker invocation alongside the skill discipline file.
+Defines the behavioral contract all workers must follow regardless of skill or model.
+
+---
 
 ## Output contract
 
-Every response is raw JSON matching the response schema. No preamble, no prose, no markdown. Malformed output is treated as a failed invocation.
+Every response is raw JSON matching the skill's output schema.
+- No preamble, no explanation, no prose before or after the JSON
+- No markdown code fences around the JSON
+- Malformed output is treated as a failed invocation
+- If uncertain, return valid JSON anyway — put uncertainty in `message`
 
 ## Quality gate
 
-`verified: true` only when a subprocess exit code confirms the outcome. Never self-assess. "I think the tests pass" is not verified.
+`verified: true` means the artifact was independently confirmed correct:
+- For code: the test runner exited 0
+- For files: the file exists at the path you wrote
+- Never set `verified: true` based on self-assessment — only on external confirmation
+- "I think the tests pass" is not verified. Run them.
 
 ## Escalation
 
-If stuck after 3 attempts, return `status: error` with a clear `message` explaining why. Do not retry silently. Do not fabricate a passing result.
+If stuck after a genuine attempt:
+- Return `status: error` with a clear reason in `message`
+- Do not retry silently or produce low-confidence output labelled as a pass
+- Do not hallucinate file paths, test results, or exit codes
+- Maximum 3 attempts per phase — if output is identical across two consecutive attempts, stop immediately
 
-## Working offline
+## Context usage
 
-If brain context is absent from your prompt, proceed using your discipline file only. Note the gap in your `message` field: "no brain context available".
+You may receive a `## Relevant knowledge` block and/or a `## Session history` block before your task.
+- **Relevant knowledge**: patterns, decisions, and conventions from past sessions. Let them inform your approach — do not contradict them without reason.
+- **Session history**: what has already happened in this session. Build on it, do not repeat it.
+- If either block is absent, proceed with the skill discipline file only. Note the absence in `message` if it materially affects quality.
 
-## Handoff format
+## Handoff discipline
 
-Structure your output so the next worker in a chain can consume it without transformation. Use the standard result schema. Do not add extra fields.
+Structure output so the next worker in a chain can consume it without transformation:
+- `file_path`: absolute path to the primary artifact you produced
+- `runner_output`: verbatim stdout+stderr from the last command you ran (truncate to 2000 chars if longer)
+- `message`: one sentence — what you did and whether it worked
+
+## Scope
+
+You have access to `Bash`, `Read`, and `Write` only.
+- Do not attempt to call MCP tools or make HTTP requests
+- Do not modify files outside `project_root` without explicit instruction
+- If the task requires capabilities you do not have, return `status: error`
 
 ## Session logging
 
-The Go skill handler records your invocation in the session log automatically. You do not need to do this yourself.
+The Go skill handler records your invocation automatically. You do not need to log anything yourself.

ingestion/internal/api/handler.go

@@ -79,7 +79,7 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
 		filename = fmt.Sprintf("%s-auto.md", time.Now().UTC().Format("2006-01-02-150405"))
 	}
 
-	rawDir := filepath.Join(h.brainDir, "raw")
+	rawDir := filepath.Join(h.brainDir, "knowledge")
 	if err := os.MkdirAll(rawDir, 0o755); err != nil {
 		http.Error(w, "failed to create raw dir", http.StatusInternalServerError)
 		return

ingestion/internal/api/handler_test.go

@@ -20,10 +20,9 @@ import (
 func setup(t *testing.T) (string, *api.Handler) {
 	t.Helper()
 	dir := t.TempDir()
-	require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki", "concepts"), 0o755))
-	require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755))
 	require.NoError(t, os.WriteFile(
-		filepath.Join(dir, "wiki", "concepts", "tdd.md"),
+		filepath.Join(dir, "knowledge", "tdd.md"),
 		[]byte("---\ntitle: TDD\ndomain: software\n---\n\nTest-driven development is a discipline.\n"),
 		0o644,
 	))
@@ -46,7 +45,7 @@ func TestQuery_ReturnsResults(t *testing.T) {
 	assert.NotEmpty(t, results)
 }
 
-func TestWrite_CreatesRawFile(t *testing.T) {
+func TestWrite_CreatesKnowledgeFile(t *testing.T) {
 	dir, h := setup(t)
 	body, _ := json.Marshal(map[string]any{
 		"content":  "# Test note\n\nSome content.",
@@ -62,8 +61,7 @@ func TestWrite_CreatesRawFile(t *testing.T) {
 	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
 	assert.NotEmpty(t, resp["path"])
 
-	written := filepath.Join(dir, "raw", "test-note.md")
-	content, err := os.ReadFile(written)
+	content, err := os.ReadFile(filepath.Join(dir, "knowledge", "test-note.md"))
 	require.NoError(t, err)
 	assert.Contains(t, string(content), "Some content.")
 }
@@ -93,7 +91,7 @@ func TestWrite_IncludesFrontmatterWhenTypeProvided(t *testing.T) {
 	h.Write(rec, req)
 
 	assert.Equal(t, http.StatusOK, rec.Code)
-	content, err := os.ReadFile(filepath.Join(dir, "raw", "typed-note.md"))
+	content, err := os.ReadFile(filepath.Join(dir, "knowledge", "typed-note.md"))
 	require.NoError(t, err)
 	assert.Contains(t, string(content), "type: concept")
 	assert.Contains(t, string(content), "domain: software")
@@ -109,7 +107,8 @@ func TestWrite_GeneratesFilenameIfAbsent(t *testing.T) {
 	h.Write(rec, req)
 
 	assert.Equal(t, http.StatusOK, rec.Code)
-	entries, _ := os.ReadDir(filepath.Join(dir, "raw"))
-	assert.Len(t, entries, 1)
-	assert.True(t, strings.HasSuffix(entries[0].Name(), ".md"))
+	entries, _ := os.ReadDir(filepath.Join(dir, "knowledge"))
+	// +1 because setup already wrote tdd.md
+	assert.Len(t, entries, 2)
+	assert.True(t, strings.HasSuffix(entries[1].Name(), ".md"))
 }

ingestion/internal/search/search.go

@@ -33,7 +33,7 @@ func Query(brainDir, query string, limit int) ([]Result, error) {
 
 	var results []Result
 
-	err := filepath.WalkDir(filepath.Join(brainDir, "wiki"), func(path string, d os.DirEntry, err error) error {
+	err := filepath.WalkDir(filepath.Join(brainDir, "knowledge"), func(path string, d os.DirEntry, err error) error {
 		if err != nil {
 			slog.Warn("search: skipping path", "path", path, "err", err)
 			return nil

ingestion/internal/search/search_test.go

@@ -14,17 +14,15 @@ import (
 
 func TestSearch_ReturnsMatchingPages(t *testing.T) {
 	dir := t.TempDir()
-	require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki", "concepts"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755))
 
-	// Write a concept page mentioning "retry"
 	require.NoError(t, os.WriteFile(
-		filepath.Join(dir, "wiki", "concepts", "retry-logic.md"),
+		filepath.Join(dir, "knowledge", "retry-logic.md"),
 		[]byte("---\ntitle: Retry Logic\ndomain: software\n---\n\nRetry logic handles transient failures by re-attempting operations.\n"),
 		0o644,
 	))
-	// Write an unrelated page
 	require.NoError(t, os.WriteFile(
-		filepath.Join(dir, "wiki", "concepts", "database.md"),
+		filepath.Join(dir, "knowledge", "database.md"),
 		[]byte("---\ntitle: Database\ndomain: software\n---\n\nA database stores structured data.\n"),
 		0o644,
 	))
@@ -32,7 +30,7 @@ func TestSearch_ReturnsMatchingPages(t *testing.T) {
 	results, err := search.Query(dir, "retry transient", 5)
 	require.NoError(t, err)
 	require.Len(t, results, 1)
-	assert.Equal(t, "wiki/concepts/retry-logic.md", results[0].Path)
+	assert.Equal(t, "knowledge/retry-logic.md", results[0].Path)
 	assert.Equal(t, "Retry Logic", results[0].Title)
 	assert.Greater(t, results[0].Score, 0)
 	assert.Contains(t, results[0].Excerpt, "Retry")
@@ -40,10 +38,10 @@ func TestSearch_ReturnsMatchingPages(t *testing.T) {
 
 func TestSearch_RespectsLimit(t *testing.T) {
 	dir := t.TempDir()
-	require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki", "concepts"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755))
 	for i := 0; i < 5; i++ {
 		require.NoError(t, os.WriteFile(
-			filepath.Join(dir, "wiki", "concepts", fmt.Sprintf("page-%d.md", i)),
+			filepath.Join(dir, "knowledge", fmt.Sprintf("page-%d.md", i)),
 			[]byte(fmt.Sprintf("---\ntitle: Page %d\n---\n\nThis page mentions retry.\n", i)),
 			0o644,
 		))

internal/brain/client.go

@@ -0,0 +1,76 @@
+// internal/brain/client.go
+// Package brain provides a lightweight client for querying the ingestion server.
+// Skill handlers call Query before spawning workers to inject relevant knowledge
+// from the brain into the task prompt. Errors are suppressed — the brain is
+// optional context; its absence must never block a skill invocation.
+package brain
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"strings"
+)
+
+type queryResult struct {
+	Path    string `json:"path"`
+	Title   string `json:"title"`
+	Excerpt string `json:"excerpt"`
+	Score   int    `json:"score"`
+}
+
+// Query calls the ingestion server and returns relevant knowledge as a
+// formatted string ready to prepend to a worker task prompt.
+// Returns empty string (no error) when baseURL or query is empty,
+// when the brain is unreachable, or when no results are found.
+func Query(ctx context.Context, baseURL, query string, limit int) (string, error) {
+	if baseURL == "" || strings.TrimSpace(query) == "" {
+		return "", nil
+	}
+	if limit <= 0 {
+		limit = 3
+	}
+
+	body, _ := json.Marshal(map[string]any{"query": query, "limit": limit})
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, baseURL+"/query", bytes.NewReader(body))
+	if err != nil {
+		slog.Warn("brain: build request failed", "err", err)
+		return "", nil
+	}
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		slog.Warn("brain: ingestion server unreachable", "err", err)
+		return "", nil
+	}
+	defer func() { _ = resp.Body.Close() }()
+
+	if resp.StatusCode != http.StatusOK {
+		slog.Warn("brain: ingestion server returned non-OK", "status", resp.StatusCode)
+		return "", nil
+	}
+
+	out, _ := io.ReadAll(resp.Body)
+	var result struct {
+		Results []queryResult `json:"results"`
+	}
+	if err := json.Unmarshal(out, &result); err != nil || len(result.Results) == 0 {
+		return "", nil
+	}
+
+	var b strings.Builder
+	b.WriteString("## Relevant knowledge\n\n")
+	for _, r := range result.Results {
+		title := r.Title
+		if title == "" {
+			title = r.Path
+		}
+		fmt.Fprintf(&b, "### %s\n%s\n\n", title, r.Excerpt)
+	}
+	return b.String(), nil
+}

internal/brain/client_test.go

@@ -0,0 +1,67 @@
+package brain_test
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/mathiasbq/supervisor/internal/brain"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestQueryEmptyBaseURL(t *testing.T) {
+	result, err := brain.Query(context.Background(), "", "tdd patterns", 3)
+	require.NoError(t, err)
+	assert.Empty(t, result)
+}
+
+func TestQueryEmptyQuery(t *testing.T) {
+	result, err := brain.Query(context.Background(), "http://localhost:9999", "", 3)
+	require.NoError(t, err)
+	assert.Empty(t, result)
+}
+
+func TestQueryFormatsResults(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		assert.Equal(t, "/query", r.URL.Path)
+		var req map[string]any
+		require.NoError(t, json.NewDecoder(r.Body).Decode(&req))
+		assert.Equal(t, "tdd patterns", req["query"])
+
+		json.NewEncoder(w).Encode(map[string]any{ //nolint:errcheck
+			"results": []map[string]any{
+				{"path": "knowledge/tdd.md", "title": "TDD Guide", "excerpt": "Always write tests first.", "score": 5},
+				{"path": "knowledge/go.md", "title": "Go Conventions", "excerpt": "Use table-driven tests.", "score": 3},
+			},
+		})
+	}))
+	defer srv.Close()
+
+	result, err := brain.Query(context.Background(), srv.URL, "tdd patterns", 3)
+	require.NoError(t, err)
+	assert.Contains(t, result, "## Relevant knowledge")
+	assert.Contains(t, result, "TDD Guide")
+	assert.Contains(t, result, "Always write tests first.")
+	assert.Contains(t, result, "Go Conventions")
+}
+
+func TestQueryEmptyResults(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		json.NewEncoder(w).Encode(map[string]any{"results": []any{}}) //nolint:errcheck
+	}))
+	defer srv.Close()
+
+	result, err := brain.Query(context.Background(), srv.URL, "obscure query", 3)
+	require.NoError(t, err)
+	assert.Empty(t, result)
+}
+
+func TestQueryUnavailableServerReturnsEmpty(t *testing.T) {
+	// Brain unavailable — should degrade gracefully, no error
+	result, err := brain.Query(context.Background(), "http://127.0.0.1:19999", "query", 3)
+	require.NoError(t, err)
+	assert.Empty(t, result)
+}

internal/skills/debug/handlers.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"time"
 
+	"github.com/mathiasbq/supervisor/internal/brain"
 	iexec "github.com/mathiasbq/supervisor/internal/exec"
 	"github.com/mathiasbq/supervisor/internal/session"
 )
@@ -40,11 +41,16 @@ func (s *Skill) Handle(ctx context.Context, tool string, args json.RawMessage) (
 		model = s.cfg.DefaultModel
 	}
 
+	brainCtx, _ := brain.Query(ctx, s.cfg.IngestBaseURL, a.Error+" "+a.Context, 3)
+
 	task := fmt.Sprintf(
 		"phase: debug\nproject_root: %s\nerror: %s\ncontext: %s\nmodel: %s",
 		a.ProjectRoot, a.Error, a.Context, model,
 	)
 	task = session.PrependHistory(s.cfg.SessionsDir, a.SessionID, "debug", task)
+	if brainCtx != "" {
+		task = brainCtx + "\n---\n\n" + task
+	}
 
 	if s.cfg.ExecutorFn == nil {
 		return nil, fmt.Errorf("no executor configured")

internal/skills/debug/skill.go

@@ -18,6 +18,7 @@ type Config struct {
 	DefaultModel  string
 	ExecutorFn    ExecutorFn
 	SessionsDir   string
+	IngestBaseURL string // optional: base URL of ingestion server for brain context
 }
 
 // Skill implements the debug MCP tool.

internal/skills/review/handlers.go

@@ -8,6 +8,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/mathiasbq/supervisor/internal/brain"
 	iexec "github.com/mathiasbq/supervisor/internal/exec"
 	"github.com/mathiasbq/supervisor/internal/session"
 )
@@ -41,11 +42,16 @@ func (s *Skill) Handle(ctx context.Context, tool string, args json.RawMessage) (
 		model = s.cfg.DefaultModel
 	}
 
+	brainCtx, _ := brain.Query(ctx, s.cfg.IngestBaseURL, strings.Join(a.Files, " ")+" "+a.Context, 3)
+
 	task := fmt.Sprintf(
 		"phase: review\nproject_root: %s\nfiles: %s\ncontext: %s\nmodel: %s",
 		a.ProjectRoot, strings.Join(a.Files, ", "), a.Context, model,
 	)
 	task = session.PrependHistory(s.cfg.SessionsDir, a.SessionID, "review", task)
+	if brainCtx != "" {
+		task = brainCtx + "\n---\n\n" + task
+	}
 
 	if s.cfg.ExecutorFn == nil {
 		return nil, fmt.Errorf("no executor configured")

internal/skills/review/skill.go

@@ -18,6 +18,7 @@ type Config struct {
 	DefaultModel  string
 	ExecutorFn    ExecutorFn
 	SessionsDir   string
+	IngestBaseURL string // optional: base URL of ingestion server for brain context
 }
 
 // Skill implements the review MCP tool.

internal/skills/spec/handlers.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"time"
 
+	"github.com/mathiasbq/supervisor/internal/brain"
 	iexec "github.com/mathiasbq/supervisor/internal/exec"
 	"github.com/mathiasbq/supervisor/internal/session"
 )
@@ -45,11 +46,16 @@ func (s *Skill) Handle(ctx context.Context, tool string, args json.RawMessage) (
 		model = s.cfg.DefaultModel
 	}
 
+	brainCtx, _ := brain.Query(ctx, s.cfg.IngestBaseURL, a.Requirements+" "+a.Context, 3)
+
 	task := fmt.Sprintf(
 		"phase: spec\nproject_root: %s\nrequirements: %s\noutput_path: %s\ncontext: %s\nmodel: %s",
 		a.ProjectRoot, a.Requirements, outputPath, a.Context, model,
 	)
 	task = session.PrependHistory(s.cfg.SessionsDir, a.SessionID, "spec", task)
+	if brainCtx != "" {
+		task = brainCtx + "\n---\n\n" + task
+	}
 
 	if s.cfg.ExecutorFn == nil {
 		return nil, fmt.Errorf("no executor configured")

internal/skills/spec/skill.go

@@ -18,6 +18,7 @@ type Config struct {
 	DefaultModel  string
 	ExecutorFn    ExecutorFn
 	SessionsDir   string
+	IngestBaseURL string // optional: base URL of ingestion server for brain context
 }
 
 // Skill implements the spec MCP tool.

internal/skills/tdd/handlers.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"time"
 
+	"github.com/mathiasbq/supervisor/internal/brain"
 	iexec "github.com/mathiasbq/supervisor/internal/exec"
 	"github.com/mathiasbq/supervisor/internal/session"
 )
@@ -41,10 +42,15 @@ func (s *Skill) handleRed(ctx context.Context, raw json.RawMessage) (json.RawMes
 	if args.Spec == "" {
 		return nil, fmt.Errorf("spec is required")
 	}
+	brainCtx, _ := brain.Query(ctx, s.cfg.IngestBaseURL, args.Spec, 3)
+
 	task := fmt.Sprintf(
 		"phase: red\nproject_root: %s\nspec: %s\nmodel: %s\ntest_cmd: %s",
 		args.ProjectRoot, args.Spec, s.resolveModel(args.Model), args.TestCmd,
 	)
+	if brainCtx != "" {
+		task = brainCtx + "\n---\n\n" + task
+	}
 	return s.execute(ctx, task)
 }
 

internal/skills/tdd/skill.go

@@ -17,6 +17,7 @@ type Config struct {
 	ExecutorFn    ExecutorFn // nil = no executor (tests that don't reach execute())
 	DefaultModel  string
 	SessionsDir   string // optional: path to brain/sessions/ for history injection
+	IngestBaseURL string // optional: base URL of ingestion server for brain context
 }
 
 type Skill struct {