Borrowing it
Nothing to install: this file belongs to cognesy/instructor-php. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cognesy/instructor-php/main/.codex/skills/instructor-release/SKILL.mdgit clone --depth 1 https://github.com/cognesy/instructor-phpWrote 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/cognesy/instructor-php/instructor-release)<a href="https://agentmods.dev/skills/cognesy/instructor-php/instructor-release"><img src="https://agentmods.dev/badge/skills/cognesy/instructor-php/instructor-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/cognesy/instructor-php/instructor-release"><img src="https://agentmods.dev/badge/skills/cognesy/instructor-php/instructor-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01491 |
| Opus 5.5 | $0.00027 | $0.00596 |
| Sonnet 5.5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
instructor-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 2mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructor Release
This skill is the repo-local release orchestrator for InstructorPHP. A release is never a loose checklist. It is always a deterministic bd workflow with explicit gates, tracked blockers, and a final approval step before publish.
Treat these files as source of truth:
AGENTS.mdfor repo rules,bd, and git ownership constraintsCONTRIBUTING.mdfor release and package-management workflowQUALITY.mdfor verification lanesscripts/release/publish-ver.shfor the actual publish pathscripts/packages/sync-ver.shfor version synchronization.github/workflows/docs.ymlfor validated Mintlify and GitHub Pages deployment.github/workflows/php.ymlfor compatibility matrix coverage.github/workflows/split.ymlfor post-tag split package publishingdocs/release-notes/*.mdxfor public release-note shape
Read these references as needed:
references/bd-release-template.mdreferences/preflight-checks.mdreferences/examples-policy.mdreferences/release-notes-template.mdxreferences/post-release.md
When To Use
Use this skill when the user asks to:
- create or ship a new version release
- prepare release notes or package-change summaries
- run release-candidate QA or production-readiness checks
- decide which tests, examples, docs checks, and CI reproductions are required before publish
- publish with
scripts/release/publish-ver.sh - prepare or post the release announcement
Release Rules
- A release always gets a
bdepic and child tasks. - Root quality gates must be green before publish unless the user explicitly accepts a waiver.
- Split-package verification must be green before publish unless the user explicitly accepts a waiver.
- Live examples are expensive. Run the curated live smoke set once per release cycle, then retry only failed examples after fixes.
- Do not publish, tag, push, or post to X without explicit approval in the current conversation.
- Do not hide failing checks. Record them in
bdnotes and block the release until resolved or explicitly waived.
What ships with it
6 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.
- 2mo ago First seen · 174 lines · 68 tokens per session scan A 2882a2f51e12
instructor-release is a skill published in the GitHub repository cognesy/instructor-php (328 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 1,491 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
dev-release-check
Use for pre-release validation, versioning, changelogs, artifacts, smoke tests, rollback notes, and release risk.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…