Retain original skill rhetoric and the frozen flavor library while adding
portable Claude Code, Codex and ChatGPT runtime contracts and packages.
Correct hook event handling, scoped numeric checkpoints, flavor locks,
plugin path resolution, advisory integrity checks and voluntary feedback.
Add native-loading and ordered-evidence runners for cc0, OMP and Codex.
Document paired model results, refusals, approval/rate-limit failures,
explanatory factual errors and remaining evidence gaps without an all-model
pass claim. Exclude private execution archives from public Git content.
Bump all six PUA manifests including Pi, refresh three-language READMEs,
and add release notes plus reproducible offline validation instructions.
Resolve optional OMP source metadata relative to the current user's home.
Validation:
- 17 offline suites passed, including 13 OMP evidence regressions
- Six manifest versions synchronized; all tested skill hashes unchanged
- Three portable packages rebuilt reproducibly; original tone checks pass
- Python, Bash and JSON syntax; public doc links; staged diff checks pass
- 330 private archive files verified unchanged and excluded from staging
Real-model results remain limited: this is not universal behavior acceptance.
Co-authored-by: Codex <codex@openai.com>
PUA Skill no longer sends anything over the network. Removed end to end,
both the client hooks that emit data and the server that received it.
Channels removed:
- Session transcript upload (/api/upload) full redacted .jsonl
- Rating feedback (/api/feedback) rating, counts, flavor
- Silent heartbeat telemetry (/api/heartbeat) install id, version, platform
- PUA leaderboard (/api/leaderboard) email, phone, PUA counts
- pua-api platform (agentguard.workers.dev)
phone + SMS registration, silent session_start/pua_triggered/command_used
events, remote prompt-template fetch, and the payment flow that depended
on the registration token
Client:
- delete hooks/heartbeat.sh; drop both SessionStart registrations
- stop-feedback.sh: 5 curl calls -> append one line to ~/.pua/feedback.jsonl
- rewrite references/platform.md as a local-only command reference
- drop the leaderboard section and commands from skills/pro
- survey/pua/offline command docs: local-only wording
Server:
- delete all Pages Functions (upload, feedback, heartbeat, leaderboard,
_sanitize, me, _session, auth/*) and all 5 D1 migrations
- contribute + admin pages become notices; no upload form, no login
- wrangler.toml: drop R2/D1 bindings and GitHub OAuth vars
Note: removing the bindings does not delete stored data. The R2 bucket
(puaskill-upload), the D1 database (pua-uploads-db) and the
GITHUB_CLIENT_SECRET / SESSION_SECRET secrets must be deleted in the
Cloudflare dashboard separately.
Guard rail:
- add evals/test-no-telemetry.sh: reverse assertions over the whole repo
(collection hosts, endpoint paths, outbound request bodies, deleted files,
hook registrations, CF bindings) plus a positive control that local
feedback still works. Verified by injecting both a naive and an evasive
upload; 4 and 2 gates fired respectively.
- test-upload-flow / test-heartbeat / test-feedback-auth asserted that
collection worked, so they were replaced rather than merely deleted --
deleting them would have removed the guard along with the feature.
hooks/sanitize-session.sh is kept as a standalone offline redaction tool.
Unlike the deleted TypeScript port it does not split input per line, so the
multiline PEM pattern still matches (issue #134 ID-001 did not apply to it).
Refs #134, #98, #100
Summary:
- Replace the one-line confidence loop with an explicit Confidence Gate
that enumerates claims, finds risks, fixes or discloses them, and
reruns evidence before delivery.
- Make pua-loop Oracle verification portable on macOS/Linux and add
hook smoke tests for verified, rejected, and quoted verify commands.
- Fix trigger/behavior evals so they use portable timeouts, isolated
PUA config, a neutral workspace, and the Claude CLI stream-json
verbose requirement.
- Tighten PUA skill and slash-command descriptions to avoid triggering
on normal first-attempt coding or information requests.
- Bump marketplace/plugin manifests to v3.2.5 with an updated Claude
marketplace changelog summary.
Rationale:
- The previous strategy relied on vague "100% confidence" wording and
left the verification system itself vulnerable to false failures on
macOS, local user config leakage, and workspace-biased false triggers.
- Confidence is now defined as evidence-backed gates: all runnable
checks pass, known high-risk issues are fixed, and residual risks are
disclosed.
Tests:
- bash -n hooks/*.sh scripts/*.sh evals/*.sh
- bash evals/test-yaml-frontmatter.sh
- bash evals/test-release-consistency.sh
- bash evals/test-pua-loop-hook.sh
- bash evals/test-behavior.sh
- bash evals/run-trigger-test.sh
Co-authored-by: Codex <codex@openai.com>
- Add mama route to commands/pua.md router (was missing entirely)
- Create commands/mama.md for /pua:mama direct invocation
- Update argument-hint and trigger list to include mama
- Fixes: /pua mama and /pua:mama now both work correctly
## Issue #97 — Hooks fire without user consent
- PreCompact hook now checks for PUA activation markers before writing files
- Stop feedback hook skips if PUA was never triggered this session
## Issue #98 — Session sanitization incomplete
- Sanitize script upgraded; rate limiting migration added (0003_feedback_rate_limiting.sql)
## Issue #99 — PUA Loop no in-session escape
- Default max iterations changed from unlimited to 30
- Added <loop-abort> (terminate) and <loop-pause> (pause for manual intervention) signals
- Loop hook supports active:false for pause state; session self-binding on resume
- Added /cancel-pua-loop command; guide.html and README updated
- PUA pressure escalation injected per iteration via system message
## Issue #100 — Upload endpoint undisclosed PII
- Privacy/data-usage disclosure added to contribute.html (ZH+EN bilingual)
- Contribute.tsx updated with same disclosure
## Additional fixes
- Rename commands/loop.md → commands/pua-loop.md; add cancel-pua-loop.md
- Replace "Ralph Loop × PUA" with "PUA Loop" across all user-facing docs
- Fix nav active-state highlighting on all sub-pages
- Fix logout button (GET method); redirect to /contribute.html
- Add JA language support to leaderboard.html
- Add "how to find session file" guide to contribute.html
- Unify nav-r gap (1rem) across all pages
Closes#97Closes#98Closes#99Closes#100
