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 skills add cmdr-chara/codex-toolkit --skill verification-and-releasegit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cmdr-chara/codex-toolkit/verification-and-release)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/verification-and-release"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/verification-and-release/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/verification-and-release"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/verification-and-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00032 | $0.00708 |
| Opus 5.5 | $0.00013 | $0.00283 |
| Sonnet 5.5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
verification-and-release 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 24d ago.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification and Release
Decide release readiness from evidence proportional to consequence, novelty, blast radius, and reversibility.
Trigger boundary
Use this skill for verification strategy, CI/test evidence review, operational release controls, rollout/rollback planning, or a final READY / CONDITIONAL / BLOCKED decision.
Do not trigger to implement the feature, diagnose an unknown failure, or treat a green unit suite as sufficient release evidence.
Required inputs
Resolve the frozen candidate/ref, intended behavior, affected consumers, risk-sensitive surfaces, local/CI results, deployment topology, migrations, observability, rollback/forward-recovery, release scope, and protected user work.
Safety baseline
- Preserve the working tree and candidate identity.
- Do not mark skipped, stale, flaky, filtered, or wrong-revision checks as passing evidence.
- Do not expose secrets in logs or evidence bundles.
- Do not deploy or roll back production merely because this skill recommends it.
Workflow
- Freeze the candidate and claims. Every check must prove or challenge a specific behavioral or nonfunctional claim.
- Map risk. Use
references/risk-test-matrix.md; risk comes from failure modes and reversibility, not line count. - Choose minimum sufficient evidence. Static, unit/component, contract/schema, integration, end-to-end, nonfunctional, and operational layers are options, not a mandatory checklist.
- Review CI architecture when needed. For GitHub Actions speed, trust boundaries, permissions, caching, or deploy gates, read
references/github-actions.md. - Collect exact results. Where JUnit/LCOV reports exist, use:
python skills/verification-and-release/scripts/summarize_test_reports.py --junit build/test-results --lcov coverage/lcov.info --format markdown
Record command, candidate, environment, pass/fail/skip/flaky state, and relevant artifacts.
6. Evaluate evidence quality. Classify material evidence as current pass, fail, gap, stale, flaky, or not applicable with reason.
7. Verify operational readiness. Check applicable build artifact, configuration, migration ordering, health, flags, observability, support/runbooks, and rollback/forward-recovery.
8. Define rollout. State cohort/staging, kill/rollback trigger, monitoring window, and post-release verification.
9. Issue the decision. Use references/release-evidence-schema.md. Residual risk acceptance belongs to the authorized owner, not the skill.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed · -128 lines · -49 tokens per session ac22fce6f3c9
- 1mo ago First seen · 184 lines · 81 tokens per session scan A 208f7d6a5cd0
verification-and-release is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 708 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
ai-agents-empirical-probe-toolkit
Prove-it methods for this repo. Six recipes for runtime-contract probes, guard and threshold calibration, eval A/B, docs-vs-reality audits, reproduce-on-main CI triage, and negative-control test design, each with a worked example from repo history. Use when you say probe the runtime contract, calibrate this guard…
loki-mode
Launch Loki Mode autonomous SDLC agent. Handles PRD-to-deployment with minimal human intervention. Invoke for multi-phase development tasks, bug fixing campaigns, or full product builds.
pr-review
Review Cool Workflow pull requests or branch diffs. Use when Codex must inspect code changes for bugs, regressions, FreeBSD/POLA violations, missing tests, generated artifact drift, release-contract risk, or CI implications, and return findings first with file/line citations.
spec-code-review
Structured code review for bugs, regressions, tests, and standards. Report-only by default; apply fixes only when the current user or upstream caller explicitly requests review-and-fix. mode:agent is always report-only.
hunt
Finds root cause of errors, crashes, unexpected behavior, and failing tests before applying any fix. Not for code review or new features.