@chrono-meta/fh-gate 1.4.0 → 1.4.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CATALOG.md CHANGED
@@ -9,7 +9,7 @@ AI reads this file first when searching past work. Open individual files for det
9
9
  <!-- Add entries in reverse date order (newest at top) -->
10
10
 
11
11
  ### 2026-06-05 | _audit | sister-asset, gstack, field-harness, garry-tan
12
- **File:** tracks/_audit/session_2026_06_05_gstack-sister.md (private mirror: fh-be)
12
+ **File:** tracks/_audit/session_2026_06_05_gstack-sister.md (private companion mirror)
13
13
  gstack (garrytan, ~66K stars) sister-asset cross-audit — the field/execution-harness counterpart to FH's meta/governance harness, both running on the Claude Code skill substrate. FH governs / gstack executes (composes, not competes). Bidirectional import (frictionless one-command install, opinionated front door, privacy-first telemetry) / propagate (post-ship governance gate, cross-project knowledge compounding, HITL promotion gate) lists recorded.
14
14
  - Decision: public index only — bet evidence (B1·ID·SB) + full audit held in private store; external cross-link proposal to garrytan/gstack gated behind 3+ persona × 4-axis audit.
15
15
 
package/README.md CHANGED
@@ -28,9 +28,9 @@
28
28
  </p>
29
29
 
30
30
  <p align="center">
31
- <a href="ETHOS.md"><b>The principles</b></a> ·
32
- <a href="WHY.md"><b>Why it exists</b></a> ·
33
- <a href="OUTPUT_EVIDENCE.md"><b>The evidence</b></a> ·
31
+ <a href="docs/ETHOS.md"><b>The principles</b></a> ·
32
+ <a href="docs/WHY.md"><b>Why it exists</b></a> ·
33
+ <a href="docs/OUTPUT_EVIDENCE.md"><b>The evidence</b></a> ·
34
34
  <a href="CHEATSHEET.md"><b>How to use it</b></a>
35
35
  </p>
36
36
 
@@ -164,7 +164,7 @@ hardened by attack, and only then does it ship faster, for having survived.
164
164
  | → **Accelerate** | a blade that survived the forge cuts faster | `goal-quench` — *Pass → Accelerate* |
165
165
 
166
166
  Three movements are shipped; **temper** is the direction ahead — and naming the movement we have *not*
167
- finished is the point (see [`ETHOS.md`](ETHOS.md#the-forge)). Around the forge, two more signatures keep
167
+ finished is the point (see [`ETHOS.md`](docs/ETHOS.md#the-forge)). Around the forge, two more signatures keep
168
168
  it running: `harvest-loop` (each session's lessons become permanent skills) and `agent-composer`
169
169
  (orchestrate the dispatch). The other skills wait until you need them — full list below.
170
170
 
@@ -286,5 +286,5 @@ External convergence:
286
286
  | [`CHEATSHEET.md`](CHEATSHEET.md) | Full command reference |
287
287
  | [`AGENTS.md`](AGENTS.md) | Runtime agent specs |
288
288
  | [`CATALOG.md`](CATALOG.md) | Past work search index |
289
- | [`CONTRIBUTING.md`](CONTRIBUTING.md) | How to contribute skills and patterns |
289
+ | [`CONTRIBUTING.md`](docs/CONTRIBUTING.md) | How to contribute skills and patterns |
290
290
  | [`fh_integration_contract.md`](knowledge/shared/harness-core/fh_integration_contract.md) | Governance gate spec |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@chrono-meta/fh-gate",
3
- "version": "1.4.0",
3
+ "version": "1.4.1",
4
4
  "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
5
5
  "license": "MIT",
6
6
  "keywords": [
@@ -45,7 +45,7 @@
45
45
  "CATALOG.md",
46
46
  "CHEATSHEET.md",
47
47
  "CLAUDE.md",
48
- "CONTRIBUTING.md",
48
+ "docs/CONTRIBUTING.md",
49
49
  "bin/fh-gate.js",
50
50
  "bin/fh-run.js",
51
51
  "bin/fh-goal.js",
@@ -420,7 +420,6 @@ fi
420
420
 
421
421
  ```bash
422
422
  if echo "$changed" | grep -q "^README\.md$"; then
423
- grep -n "chrono-code" README.md 2>/dev/null && echo "STALE: 'chrono-code' found — should be 'chrono-meta'" || true
424
423
  actual=$(ls -d plugins/fh-meta/skills/*/ plugins/fh-commons/skills/*/ 2>/dev/null | wc -l | tr -d ' ')
425
424
  readme_count=$(grep -oE '[0-9]+ (fh-meta[^)]+)?skills' README.md 2>/dev/null | head -1 || echo "not found")
426
425
  echo "Actual skills: $actual | README mentions: $readme_count"
@@ -276,7 +276,7 @@ Consumer agent attempts actual use (not just reads and judges). Grades: F (funct
276
276
 
277
277
  ## Step 1.5 — Persona Output Protocol + Neutral Synthesizer (parallax)
278
278
 
279
- Generalized from the field `deep-insight` multi-persona pattern (fh-be #7), domain-stripped — the *pattern*
279
+ Generalized from the field `deep-insight` multi-persona pattern (private companion store), domain-stripped — the *pattern*
280
280
  is renamed **parallax** for public FH (it is a mode of this skill, not a separate skill — see asset-placement
281
281
  2026-06-06). It gives the persona dispatch above a shared output contract + a neutral aggregator, so
282
282
  multi-persona findings stay comparable and the synthesis injects no bias of its own.
@@ -328,7 +328,7 @@ supplies the specialist lens. Same ①installed → ②fallback → ③fetch pri
328
328
  external harness's review-skills count as ① installed sources, widening the persona pool without FH
329
329
  shipping every specialist.
330
330
 
331
- > **Absence check — resolved (added above)**: the clean replication (fh-be RESULT9 Arm F: identical
331
+ > **Absence check — resolved (added above)**: the clean replication (companion-store experiment, Arm F: identical
332
332
  > artifact, explicit omission prompt, ownership-only variable) found self ≈ isolated (~90% overlap) —
333
333
  > **omission-detection is self-administrable when explicitly asked**, refuting the earlier "the author
334
334
  > can't see their own omissions" (Arm E, a prompt/design-drift artifact). So the Absence check is a
File without changes