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 leifericf/agentic-sdk --skill write-changeloggit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/write-changelog)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/write-changelog"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-changelog.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.01118 |
| Opus 5 | $0.00024 | $0.00559 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
write-changelog 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-changelog
The changelog is written for users of the project; the commit log is
written for maintainers. Same change, two audiences. Voice rules:
skills/shared/references/prose-style.md. Mechanics: during a fix loop
the editor and writer agents do not edit the changelog file, they return
their CHANGELOG: lines (see apply-findings), the orchestrator holds
them in context, and places them into the changelog at land time. The
changelog is the committed, durable artifact; the lines reach it as
return values, never as files read back from disk.
Stage gate: alpha and beta projects keep no changelog
Before authoring or placing any entry, check the project's stage. The
descriptor's version string or the project's stated release line carries
it. If the project is in alpha or beta (version suffix -alphaN,
-betaN, or any prerelease tag; CalVer or SemVer alike), the project
keeps no CHANGELOG.md at all. Return immediately with no entry; do
not create the file, do not append to it, do not return CHANGELOG:
lines from editors or writers.
Rationale: an alpha or beta surface is shifting too fast for a changelog to carry signal. Every entry would either describe a surface that gets retracted next week or duplicate what the commit log already says. The changelog starts with the first stable release. Until then, the commit log is the history; the README's versioning section is the contract.
If you are asked to cut a release on an alpha or beta project, refuse the changelog step. The version tag and the release notes (if any) are the only artifacts.
When the project crosses to stable (v1.0, the first unqualified
CalVer date, or whatever the project's stage convention marks as
stable), the first stable release creates CHANGELOG.md with a top
heading, the first version section, and the entries accumulated since
the stage decision. From there the rituals below apply.
Does it deserve an entry?
Yes: behavior a user can observe changed. A new surface (a menu, a view, a scripting entry point), a fix to wrong output, a crash, a glitch, performance a user would notice (frame rate, throughput), anything security-relevant (always), removed or changed surface.
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.
- 4d ago First seen · 101 lines · 49 tokens per session scan A 58665b8f5b28
write-changelog is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 1,118 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.