Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/itdojp/ae-framework/hook-feedbackgit clone --depth 1 https://github.com/itdojp/ae-frameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02040 |
| Opus 5 | $0.00000 | $0.01020 |
| Sonnet 5 | $0.00000 | $0.00408 |
| Haiku 4.5 | $0.00000 | $0.00204 |
Grade A, and why
hook-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook Feedback Adapter
🌍 Language / 言語: English | 日本語
English
This is the minimal adapter that normalizes existing CI and evidence artifacts into short feedback that Claude Code and Codex can feed back into the next continuation step without manual reshaping.
Standard outputs
- JSON:
artifacts/agents/hook-feedback.json - Markdown:
artifacts/agents/hook-feedback.md - schema:
schema/hook-feedback.schema.json - builder:
node scripts/agents/build-hook-feedback.mjs PR Maintenance(.github/workflows/pr-ci-status-comment.yml) generates the adapter output in report-only mode when it can download theverify-lite-reportartifact for the same head SHA
Inputs
- required:
artifacts/verify-lite/verify-lite-run-summary.json - optional:
artifacts/ci/harness-health.json - optional:
artifacts/change-package/change-package.json - present-only:
artifacts/context-pack/context-pack-suggestions.json - present-only:
artifacts/assurance/assurance-summary.json - present-only:
artifacts/e2e/ui-e2e-summary.json
Contract fields
status:ok | warn | blockedblockingReasons[]: short list of blocking or warning reasonsnextActions[]: the next actions the operator or agent should take as-isreproCommands[]: local reproduction commandsevidence[]: artifacts to inspect nextsource: resolved input artifact paths
Minimal usage
pnpm run hook-feedback:build \
--verify-lite-summary artifacts/verify-lite/verify-lite-run-summary.json
The builder still runs when harness-health, change-package, context-pack-suggestions, assurance-summary, or ui-e2e-summary are missing. Missing artifacts are reflected through blockingReasons, nextActions, evidence.present=false, and source.*Path=null.
Optional inputs example
pnpm run hook-feedback:build \
--verify-lite-summary artifacts/verify-lite/verify-lite-run-summary.json \
--harness-health artifacts/ci/harness-health.json \
--change-package artifacts/change-package/change-package.json \
--context-pack-suggestions artifacts/context-pack/context-pack-suggestions.json \
--assurance-summary artifacts/assurance/assurance-summary.json \
--ui-e2e-summary artifacts/e2e/ui-e2e-summary.json
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 188 lines · 0 tokens per session scan A 629e0729a9fb
hook-feedback is an agent published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,040 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
playwright-test-healer
Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…
playwright-test-planner
Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…
codex
Production OpenAI-Codex-capable rootfs/initramfs.
claude
Production Claude-capable rootfs/initramfs.
doc-style
Markdown documentation prose — RFCs, ADRs, files under docs/, and READMEs — follows the same one-paragraph-per-line rule as commit messages. Write each paragraph on a single line; do not hard-wrap prose to a fixed column. The renderer reflows it to the reader's display width, whereas manual mid-paragraph line breaks…