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 skills/cognesy/instructor-php/instructor-releasenpx skills add cognesy/instructor-php --skill instructor-releasegit clone --depth 1 https://github.com/cognesy/instructor-phpWhat 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 | $0.00068 | $0.01491 |
| Opus 5 | $0.00034 | $0.00745 |
| Sonnet 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 2d 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.
- 2d 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 (326 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,491 once invoked, about $0.0003 per session on Opus 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
final-release-review
Perform pre-release planning or a final release-candidate review for openai-agents-python by comparing the target with the previous remote tag, determining the minimum compatible release type, auditing regressions and contract changes, reviewing open documentation PR coverage, drafting minor-release Key Changes, and…
release-candidate-prep
Preflight and prepare an OpenAI Agents Python release candidate in a dedicated worktree from exact origin/main, gate readiness before branch creation, freeze the released API contract, create or replace the local release branch with one release commit, enforce final release review as a checker, and produce…
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…