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/raichominev/conciliumWrote 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/raichominev/concilium/concilium-review)<a href="https://agentmods.dev/commands/raichominev/concilium/concilium-review"><img src="https://agentmods.dev/badge/commands/raichominev/concilium/concilium-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/raichominev/concilium/concilium-review"><img src="https://agentmods.dev/badge/commands/raichominev/concilium/concilium-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 | $0.00019 | $0.00702 |
| Opus 5 | $0.00010 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
concilium-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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a review round on: $ARGUMENTS
A different model lineage probes the claim adversarially and proposes a verdict; you, the
calling session, ratify it. Read references/contract.md (what the reviewer is bound to) and
SKILL.md → Ratification protocol before the first round.
Run it
--diff [base]→ review the working-tree diff:scripts/concilium-review.sh diff [base](Windows:powershell -ExecutionPolicy Bypass -File scripts/concilium-review.ps1 -Diff [-Base <branch>])- otherwise treat
$ARGUMENTSas the claim:scripts/concilium-review.sh claim "$ARGUMENTS"(Windows:... concilium-review.ps1 -Claim "$ARGUMENTS")
Run it in the background with a full ~10 min timeout from the first call — research-tier rounds
take 5–15 minutes and a foreground timeout kills the probe mid-flight. On timeout prefer a FRESH
round over a resume; if you must resume, use the full re-pin recipe in SKILL.md (a bare
codex exec resume silently resets model AND sandbox to the user's config defaults).
Tier: -Mechanical / MECHANICAL=1 for a mechanical check of a known claim; the default research
tier for open questions. Extra-family seats are opt-in — use concilium-review-kimi.* or
concilium-review-cursor.* only when the user asks for one.
After it returns
- Read the actual probe — the queries and commands, not the prose summary. An extremal 0% or 100% on a first attempt is a tripwire for a wrong join key or wrong scope, not a discovery.
- Show the five blocks (
PROBE / ALT / CAVEAT / VERDICT-PROPOSAL / PHASE-LOG) verbatim. - Give your ratified tag and one sentence of reasoning. The proposal is input, not the answer, and same-family agreement is weak evidence — weigh a dissent by lineage, never by how confident it sounds.
- If the round is disputed and you have an evidence-backed objection, loop: write this round's
probe plus the objection to a rounds file and pass it as
-PriorRounds/PRIOR_ROUNDS. Stop on convergence, on a dry round, or at the round cap.
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 · 51 lines · 19 tokens per session scan A 3ece5dc6dc3b
concilium-review is a command published in the GitHub repository raichominev/concilium (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 19 tokens to every session and 702 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 2026-08-31.
Other commands, from other repositories
code-audit
Adversarial code review tree. Wraps /cc-tree:tree with the code-audit preset preselected — finds security / performance / correctness / contract findings a static linter would miss. Every finding carries file:line evidence + threat-model context + proposedfix; hard-banned against NEEDS-MORE-INFO deferrals.…
genshijin-review
A compact Japanese-language code-review command that reports one finding per line with a severity label and suggested fix.
review
Recent git commits: !git log --oneline -10.
review-open-prs
Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.
register-plugin-asset
A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.
review
/review [optional: specific files or PR number].