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/JackScammell/Parliament-Of-ChaosWrote 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/commands/jackscammell/parliament-of-chaos/changelog-review)<a href="https://agentmods.dev/commands/jackscammell/parliament-of-chaos/changelog-review"><img src="https://agentmods.dev/badge/commands/jackscammell/parliament-of-chaos/changelog-review/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/commands/jackscammell/parliament-of-chaos/changelog-review"><img src="https://agentmods.dev/badge/commands/jackscammell/parliament-of-chaos/changelog-review.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 | $0.00014 | $0.01593 |
| Opus 5.5 | $0.00006 | $0.00637 |
| Sonnet 5.5 | $0.00003 | $0.00319 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade A, and why
changelog-review 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog Review
Fetch the Claude Code changelog, identify only new entries since the last review, and run a structured deliberation to propose implementation plans for Parliament of Chaos.
Usage
/changelog-review [--mode fast|consensus|deep] [--focus <area>] [--full]
Examples:
/changelog-review # Only new entries since last review
/changelog-review --full # Review entire changelog (first run or reset)
/changelog-review --mode deep # Deep analysis of new entries
/changelog-review --focus hooks # Only hook-related new entries
Options
-
--mode(optional): Deliberation mode for evaluating featuresfast: Quick 3-round assessment (default)consensus: Balanced 5-round evaluationdeep: Thorough 7-10 round analysis
-
--focus(optional): Filter to a specific areahooks: New hook events and capabilitiesagents: Agent system changes (frontmatter, teams, isolation)plugins: Plugin system enhancementscommands: New CLI commands and featuresperformance: Performance and token optimisationsall: Everything (default)
-
--full(optional): Ignore the last-reviewed marker and review the entire changelog. Useful for first run or to reset the review state.
State Tracking
The command maintains a state file at ${CLAUDE_PLUGIN_DATA}/changelog-review/last-reviewed.json:
{
"last_reviewed_version": "v2.1.78",
"last_reviewed_date": "2026-03-18",
"parliament_version": "1.4.0",
"entries_reviewed": 45,
"features_proposed": 12,
"features_implemented": 8
}
This file is updated after each review so that subsequent runs only process new changelog entries.
Process
- Load Review State
- Read
${CLAUDE_PLUGIN_DATA}/changelog-review/last-reviewed.json - If file does not exist or
--fullis passed, treat as first run (review everything) - Extract
last_reviewed_versionto determine the cutoff point
- Read
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.
- 1mo ago First seen · 181 lines · 14 tokens per session scan A 274ececaafe9
changelog-review is a command published in the GitHub repository JackScammell/Parliament-Of-Chaos (4 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,593 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
generate-changelog
Génération Automatique du Changelog.
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
lavra-ship
Fully automated ship sequence from code-ready to PR-open with beads closed and knowledge captured.
changelog
Create engaging changelogs for recent merges to main branch.
release-checklist
Obsolète (retirée en 9.0) : utilisez /gate:check release.