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 peteski22/agent-pragma --skill star-chambergit clone --depth 1 https://github.com/peteski22/agent-pragmaWrote 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/peteski22/agent-pragma/star-chamber)<a href="https://agentmods.dev/skills/peteski22/agent-pragma/star-chamber"><img src="https://agentmods.dev/badge/skills/peteski22/agent-pragma/star-chamber/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/peteski22/agent-pragma/star-chamber"><img src="https://agentmods.dev/badge/skills/peteski22/agent-pragma/star-chamber.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 | $0.00022 | $0.00545 |
| Opus 5 | $0.00011 | $0.00272 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
star-chamber 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 10d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Star-Chamber: Multi-LLM Craftsmanship Council
This skill is for explicit /star-chamber invocations with live progress in the main conversation. It supports --debate for multi-round deliberation. For automatic invocation on architectural decisions, the star-chamber agent handles that separately.
Advisory skill that fans out code reviews and design questions to multiple LLM providers (Claude, OpenAI, Gemini, etc.) and aggregates their feedback into consensus recommendations.
Arguments
| Flag | Description | Manual Only |
|---|---|---|
--provider <name> |
LLM provider to use (repeatable, e.g., --provider openai --provider gemini). Defaults to all in config. |
No |
--file <path> |
Specify file to review (repeatable). Defaults to recent git changes. | No |
--timeout <seconds> |
Timeout per provider request (overrides config timeout_seconds). |
No |
--debate |
Enable debate mode: multiple rounds with summarization between rounds. | Yes |
--rounds N |
Number of debate rounds (default: 2, requires --debate). | Yes |
Manual-only flags are skill invocation parameters interpreted by Claude Code, NOT flags passed to the star-chamber CLI. Debate mode is orchestrated by Claude Code (see Debate Mode in the protocol).
Path Setup
The skill loader provides the base directory in the header: Base directory for this skill: <path>. Set the path variable used throughout the protocol:
STAR_CHAMBER_PATH="<base directory from header>"
# e.g., STAR_CHAMBER_PATH="$HOME/.claude/plugins/cache/pragma/skills/star-chamber"
Protocol
Read and follow the full protocol from $STAR_CHAMBER_PATH/PROTOCOL.md. It contains Steps 0-4: prerequisite checks, invocation mode detection (code review vs design question), review target identification, context gathering, CLI invocation, and result presentation. Debate mode is documented as a separate section.
Auto-Invocation
This skill is not auto-invoked (model-invocable: false). The star-chamber custom subagent handles auto-invocation based on its description. This skill is for explicit /star-chamber invocations only.
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.
- 10d ago First seen · 43 lines · 22 tokens per session scan A 93e6a837e3df
star-chamber is a skill published in the GitHub repository peteski22/agent-pragma (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 545 once invoked, about $0.0001 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
goal-pr
Drive a pull request to a clean state and merge it: run the review-pr skill, fix every mid-or-above finding, and repeat until no mid-or-above findings remain, then merge. Use when the user wants to finish a PR by reviewing, fixing, and merging it, or triggers on "the goal-pr skill".
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
post-review-comments
Post line-level review comments and an overall review comment on a PR in English with a natural, concise writing style.
approve
Approve a pull request using gh pr review --approve.
diff-analyze
Analyze the differences between the current branch and origin/main, and summarize the current work progress.
agent-team
Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid findings.