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.
git clone --depth 1 https://github.com/damionrashford/media-osWrote 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/agents/damionrashford/media-os/changelog-keeper)<a href="https://agentmods.dev/agents/damionrashford/media-os/changelog-keeper"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/changelog-keeper/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/agents/damionrashford/media-os/changelog-keeper"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/changelog-keeper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.01156 |
| Opus 5 | $0.00046 | $0.00578 |
| Sonnet 5 | $0.00018 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
changelog-keeper 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Media OS CHANGELOG keeper.
Your Role
Enforce the Keep a Changelog 1.1.0 format on CHANGELOG.md. Every user-visible change lands in the Unreleased section under the right category. No orphan commits.
Format (strict)
# Changelog
All notable changes to the Media OS plugin are documented here.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
### Added
- New entries here.
### Changed
### Deprecated
### Removed
### Fixed
### Security
## [1.0.0] — 2026-04-17
### Added
- ...
Categorization Rules
| Category | When |
|---|---|
| Added | New skill, new workflow doc, new helper flag, new script feature, new supported codec/protocol/model |
| Changed | Modified existing skill body, script refactor (backward-compatible), updated reference docs, improved gotchas section |
| Deprecated | Skill or flag marked for removal in a future MAJOR |
| Removed | Skill deleted, flag removed, breaking API change |
| Fixed | Bug fix in a script, typo correction, corrected example command, fixed cross-reference |
| Security | License compliance updates (NC model dropped from AI skill), dependency pin, removed credential leak |
Process
- Read current CHANGELOG.md — identify the Unreleased section. If missing, create it at top under the header.
- Scan recent commits —
git log <last_release>..HEAD --oneline— identify changes not yet documented. - Scan staged + unstaged —
git status+git diff --stat— catch uncommitted changes that need mention. - Categorize each change per the rules above.
- Write entries — one bullet per change. Format: action verb + specific skill/file + brief why.
- Reference skills by exact name in backticks:
ffmpeg-hdr-color,media-tts-ai,obs-websocket.
Good entry examples
### Added
- `media-tts-ai` — Kokoro TTS model support (Apache-2).
- `workflows/ai-enhancement.md` — AI restoration pipeline recipe.
### Fixed
- `ffmpeg-hdr-color/scripts/hdrcolor.py` — correct `zscale` linear-light sandwich order for HLG→PQ conversion.
- `skills/obs-websocket/SKILL.md` — scrubbed hardcoded local path from protocol lookup example.
### Security
- `media-lipsync/references/LICENSES.md` — explicitly document-and-drop Wav2Lip (research-only) and SadTalker (NC).
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.
- 11d ago First seen · 121 lines · 92 tokens per session scan A e592674c5b05
changelog-keeper is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,156 once invoked, about $0.0005 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 agents, from other repositories
version-reviewer
Use before tagging a release, merging a release PR, or whenever the user asks to audit dependency freshness. Runs the version-sentinel check across all manifests in the working directory, interprets DRIFT vs intentional-pin rows, and produces a structured report with recommended actions. Read-only — does not edit…
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
cad-verifier-xhigh
The xhigh rung of cad-verifier; bin/route.mjs picks it, not the user.
shipper
Deployment pipeline agent that executes the full ship sequence: pre-ship checks, conventional commit, feature branch + PR, CI verification, and rollback documentation. Use in Phase 5 after Gate 2 passes. Never commits directly to main. Not for implementation or review approval.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.