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-changelog-as-marketinggit 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-changelog-as-marketing)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-changelog-as-marketing"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-changelog-as-marketing/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-changelog-as-marketing"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-changelog-as-marketing.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 | $0.00114 | $0.02509 |
| Opus 5 | $0.00057 | $0.01255 |
| Sonnet 5 | $0.00023 | $0.00502 |
| Haiku 4.5 | $0.00011 | $0.00251 |
Grade A, and why
prd-v08-changelog-as-marketing 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 13d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog as Marketing
Position in workflow: v0.8 Release Planning → v0.8 Changelog as Marketing → v0.9 Launch Channels (ORB)
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | One release format (markdown for site); one channel mapping; minimum-viable changelog page |
| standard | Release categorization + 2–3 channel mappings; per-channel format templates; publish cadence; attribution plan |
| deep | Full categorization taxonomy; format templates for all relevant channels (email, blog, Twitter, LinkedIn, RSS, Slack); cadence + voice guide; KPI- attribution per channel |
What This Does
Treats the changelog as a distribution surface, not an engineering record. Each shipped release becomes a content artifact that lands across Owned and Rented channels with minimal extra effort. This is the bridge between v0.8 (what shipped) and v0.9 (where it gets told).
Done well, this is one of the highest-leverage Owned-channel investments — Stripe, Linear, Vercel, and Sentry have shown that an opinionated changelog drives ongoing inbound that compounds over years. Done badly, it's a dumping ground for "fixed bug X" that nobody reads.
How It Works
- Define the changelog audience(s) — Engineering changelogs (for users running self-hosted or integrating an API), customer-facing changelogs (for end-users), and internal changelogs (for the team) have different shapes. Anchor to the Positioning best-fit segment.
- Categorize release content — Each shipped item gets a category:
- New feature (publish loudly)
- Improvement (publish, briefly)
- Breaking change (publish, prominently, with migration path)
- Deprecation (publish, with timeline)
- Fix (publish only if user-visible)
- Internal (don't publish externally)
- Map categories to channels — Each category gets a channel destination from the ORB mix:
- New feature → Blog post + email + Twitter + LinkedIn
- Breaking change → Email (high-priority) + RSS + blog
- Improvement → Blog (digest) + Twitter (digest)
- Fix → Changelog page only
- Build per-channel format templates — Each channel has a length/tone constraint:
- Email: subject line + 2-paragraph body + CTA
- Blog: full writeup, screenshots, code samples
- Twitter/X: 280 chars, one image
- LinkedIn: 1,000-1,500 chars, professional voice
- Slack/Discord: short with link to blog
- RSS: full content for engineering audiences
- Set publish cadence — Per-release (every shipped release publishes immediately) vs. digest (weekly/monthly roll-up). Most teams need both: per-release for big things, digest for the rest.
- Plan attribution — Every channel-published release gets a UTM. Track changelog → signup conversion to identify which categories convert.
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.
- 13d ago First seen · 210 lines · 114 tokens per session scan A 448d9f190fb8
prd-v08-changelog-as-marketing is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 12d ago), licensed MIT. It adds 114 tokens to every session and 2,509 once invoked, about $0.0006 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
release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
git-mirror-audit
Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
source-command-update-infos-release
Update Codex releases tracking (guide + landing + version bump).