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 mattgierhart/PRD-driven-context-engineering --skill prd-v08-release-planninggit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v08-release-planning)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-release-planning"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-release-planning/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/mattgierhart/prd-driven-context-engineering/prd-v08-release-planning"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-release-planning.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 | $0.00078 | $0.02951 |
| Opus 5 | $0.00039 | $0.01476 |
| Sonnet 5 | $0.00016 | $0.00590 |
| Haiku 4.5 | $0.00008 | $0.00295 |
Grade A, and why
prd-v08-release-planning 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 10d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Planning
Position in workflow: v0.7 Implementation Loop → v0.8 Release Planning → v0.8 Runbook Creation
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | Staging→prod only; 3–5 release criteria; one rollback trigger |
| standard | Dev/staging/preview/prod environments; full criteria checklist; multiple rollback triggers; post-deploy validation |
| deep | Full environments + IaC review + canary/blue-green strategy + risk-weighted criteria + post-mortem hooks |
Consumes
This skill requires prior work from v0.7 Implementation Loop and v0.6-v0.9:
- EPIC-* completed entries (from v0.7 Implementation Loop) — Finished work packages define what's being released; must have State=Complete, all TEST- passing
- TEST-* test entries (from v0.7 Test Planning) — All TEST- must pass in staging before release criteria can be met
- API-* endpoint contracts (referenced in EPIC Context & IDs) — Define SLA and performance baselines for release criteria
- ENV-* environment specifications (from v0.6 Environment Setup) — Local/CI/CD/production configurations inform DEP- entries for each environment
- ARC-* architecture decisions (from v0.6 Architecture Design) — System structure (monolith, microservices, deployment topology) drives environment setup
- TECH-* technology stack (from v0.5 Technical Stack Selection) — Technology choices inform infrastructure requirements and deployment tooling
- RISK-* high-priority entries (from v0.5 Risk Discovery) — High RISK- must be mitigated or explicitly accepted before release
- KPI-* metrics (from v0.3 and v0.9) — Target KPI values inform monitoring baselines and rollback thresholds
This skill assumes v0.7 Implementation is complete with all EPIC- entries marked Complete and all TEST- passing.
What ships with it
4 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.
- 10d ago First seen · 330 lines · 78 tokens per session scan A 599eeaab8c74
prd-v08-release-planning is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 2,951 once invoked, about $0.0004 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.