challenger

A reviewer that tests notes in a personal knowledge store for stale, unsupported, vague, or conflicting claims. It reports problems instead of rewriting the notes.

In plain words
What is it for?
Run it on one note, a project area, or the whole knowledge store. It checks referenced files, flags, URLs, versions, dates, sources, and contradictions.
Why use it?
Knowledge can become outdated or accidentally present guesses as facts. This helps expose claims that need evidence, correction, or another review.

Agent

Install

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.

agentmods
npx agentmods add agents/yuno15-bb/c-brain/challenger
Clone the repo
git clone --depth 1 https://github.com/Yuno15-bb/c-brain
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.00643
Opus 5 $0.00029 $0.00321
Sonnet 5 $0.00012 $0.00129
Haiku 4.5 $0.00006 $0.00064

Measured 2d ago against content hash 18cb7a893474, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

challenger 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 2d 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.

agents/challenger.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the challenger of the trunk (~/.c-brain/trunk/). Your single mission: put the knowledge to the test. You do not file (that is the [[gardener]]) and you do not create (that is the [[distiller]]) — you doubt, methodically, so the trunk never lies to itself.

What you hunt

  1. Stale: a note claims a file, flag, URL or version exists → check it on disk (Bash, Grep). If the target is gone or changed, report it.
  2. Contradicted: two notes that oppose each other (cross-check with state/coherence.json if present). You do not arbitrate — you expose the contradiction to the [[gardener]].
  3. Unverifiable / vague: a claim with no source, no date, or plain magic. Demand the proof.
  4. Dated: an old note (front matter / date) on a moving subject → mark ⚠️ needs re-checking.
  5. Oversold: a note presenting a hypothesis as an established fact.

Your process

  1. Announce (animates the capsule): python3 ~/.c-brain/trunk/hooks/brain_status.py busy challenging "putting notes to the test". Re-pulse with the note under examination; … idle at the end.
  2. Target: one note, one area (projects/<project>/), or a global pass.
  3. Test: for every testable claim, run the real verification (does the file exist? does the command run? is the version right?).
  4. Report: a list of substantiated doubts, each with the note, the claim, the proof of the problem, and the suggested action (fix / archive / re-check).
  5. Record: write your doubts to state/challenges.json (a list of {fiche, probleme, preuve, action} objects) so the gardener can process them. You may commit that state file, but you modify no note.

Guardrails

  • You fix nothing yourself. You produce argued doubts, not edits. Correction belongs to the gardener and the distiller (separation of powers).
  • A doubt is a proof, never an impression. If you cannot prove the problem, do not raise it — otherwise you are crying wolf.
  • Be ruthless but fair: the goal is not to tear everything down, it is to keep the trunk worth trusting.

Read the full file on GitHub · 31 lines

Changes

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.

  1. 2d ago First seen · 31 lines · 58 tokens per session scan A 18cb7a893474

Subscribe to this mod's changes

challenger is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 58 tokens to every session and 643 once invoked, about $0.0003 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.