Borrowing it
Nothing to install: this file belongs to marcusrbrown/systematic. 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/marcusrbrown/systematic/main/.agents/skills/release-notes-narrative/SKILL.mdgit clone --depth 1 https://github.com/marcusrbrown/systematicWrote 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/marcusrbrown/systematic/release-notes-narrative)<a href="https://agentmods.dev/skills/marcusrbrown/systematic/release-notes-narrative"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/release-notes-narrative/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/marcusrbrown/systematic/release-notes-narrative"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/release-notes-narrative.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 | $0.00051 | $0.03758 |
| Opus 5.5 | $0.00020 | $0.01503 |
| Sonnet 5.5 | $0.00010 | $0.00752 |
| Haiku 4.5 | $0.00005 | $0.00376 |
Grade A, and why
release-notes-narrative 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 7d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Narrative
CI Automation
This skill also runs automatically post-publish via .github/workflows/release-notes.yaml (triggered by release: published, or a manual dispatch with a tag input to re-narrate). That workflow runs scripts/dispatch-release-notes.sh, which dispatches fro-bot.yaml with a prompt that loads this skill and applies the 13-step procedure against the just-published tag. Manual invocation remains the canonical path for retroactive patches and historical releases; CI automation handles forward-going releases without operator intervention.
If you are reading this as the dispatched Fro Bot run, the prompt embedded the target tag and a correlation token. Echo the correlation token as your first log line, then proceed with the procedure below.
In CI the prompt also names a Scratch directory, $RUNNER_TEMP/fro-bot-response/release-notes — the ONLY directory you may write to (the agent runtime denies every external path except $RUNNER_TEMP/fro-bot-response/*, including /tmp and /tmp/opencode). $RUNNER_TEMP is unexpanded in the prompt: run echo "$RUNNER_TEMP" first, because file tools need absolute paths, then mkdir -p the directory. Export the resolved path as SCRATCH_DIR; Steps 3, 12, and 13 use it in place of their local default paths. Local, non-CI runs leave SCRATCH_DIR unset and keep the defaults.
Overview
@semantic-release/release-notes-generator with the conventionalcommits preset builds release bodies from commit subject lines only — commit bodies and PR descriptions are never ingested. The result is mechanically correct but qualitatively thin: a bucket of one-line bullets that tells readers what changed but not why it matters. The same generator also misparses any path#fragment substring in a commit body as a Closes #N footer, emitting broken autolinks pointing at nonexistent issues.
This skill replaces the auto-generated body with AI-assisted narrative drawn from the commit log and, when the commit body is thin, from the PR description. It applies the patch via gh release edit --notes-file against an already-published release.
What ships with it
2 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.
- 7d ago Changed ad2376707443
- 24d ago Changed · +3 lines 6a571f739e2a
- 2mo ago First seen · 287 lines · 51 tokens per session scan A 7cf66b1a8d08
release-notes-narrative is a skill published in the GitHub repository marcusrbrown/systematic (28 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 3,758 once invoked, about $0.0002 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.
release-notes-narrative compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-notes-narrativemarcusrbrown/systematic | Skill | 28 | today | MIT | A | 51 | Claude Code |
| releaseYeachan-Heo/oh-my-claudecode | Skill | 41k | yesterday | MIT | A | 27 | Claude Code |
| flow-next-landgmickel/flow-next | Skill | 717 | yesterday | MIT | A | 35 | Claude Code, Codex |
| commit-prZaxbyHub/opencode-swarm | Skill | 518 | today | MIT | A | 100 | Codex |
| re0-releaseLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 40 | Claude Code |
| get-unpublished-changescode-yeongyu/oh-my-openagent | Skill | 71k | yesterday | none | A | 38 | Claude Code, Codex |
| last-tagumputun/cc-thingz | Skill | 493 | 3d ago | MIT | A | 50 | Claude Code |