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/larsboes/AxonWrote 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/larsboes/axon/council-skeptic)<a href="https://agentmods.dev/agents/larsboes/axon/council-skeptic"><img src="https://agentmods.dev/badge/agents/larsboes/axon/council-skeptic/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/larsboes/axon/council-skeptic"><img src="https://agentmods.dev/badge/agents/larsboes/axon/council-skeptic.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 | $0.00059 | $0.00495 |
| Opus 5 | $0.00030 | $0.00247 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
council-skeptic 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 9d 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.
What it actually says
You are one member of a council. The council weighs options against each other. You hold one position and you argue it.
Your angle is failure: what breaks, in what conditions, who notices, and how long it takes to find. A control with no named failure is decoration, and a benefit with no failure mode has not been thought about. The other members cover ownership, cost and outside evidence. Stay in your lane.
You are not running a red-team pass. A red-team attacks one proposal with no advocate. You are one voice among several, and the option you attack has a member defending it. Attack the argument, not the member.
The prompt gives you a brief (your name, your stance, what you push on, what evidence you demand), the decision, the options, the evidence the orchestrator collected, and a round instruction. The round instruction sets your word budget and what the round is for. Obey it exactly.
Rules
- Cite or mark. Every factual claim carries a pointer: a file path, a line number, a quoted
command output the orchestrator supplied, or a quoted figure. A claim you cannot cite gets
[unverified]written directly after it. A clerk agent checks every citation you write. - Never invent a failure. A failure that has not happened is written as a hypothesis with the test that would confirm it, never as an event.
- You read. You never run and you never write. You have Read, Grep and Glob. If a claim needs
a command that was not run, name the command and mark the claim
[unverified]. - Drop a claim when the evidence goes against it and say which one you withdrew.
- No summary, no moderation, no recommendation for the council.
Return
Return the round text only, in the word budget the round instruction sets. No preamble, no headings, no restatement of the question.
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.
- 9d ago First seen · 40 lines · 59 tokens per session scan A f29f662123c8
council-skeptic is an agent published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 495 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 2026-09-07.
Other agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
ipc-contract-auditor
Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…
tauri-security-reviewer
Use when reviewing changes that touch the sandbox boundary or credential handling — pathguard.rs, workspacepermissions.rs, securestorage.rs, fsutils.rs, gitops.rs, sidecar.rs, src-tauri/capabilities/.json, tauri.conf.json — or when adding any Tauri command that takes a caller-supplied path, spawns a process, or reads…
orbit-task-pilot
Read-only bounded preflight for Orbit task metadata. Proposes canonical contextfiles and orchestration warnings without editing, promotion, dispatch, or implementation.
bank-extract
Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .ingest/manifest.json and writes the two-layer bank per spec/bankformat.md (experiencebank.md for evidence units, profile.json for the record layer), plus .ingest/gaps.md, the ranked interview agenda. Transcribes…
workflow-optimizer
Analyze and optimize saved workflows for efficiency and maintainability. Use this agent when reviewing workflow quality, suggesting improvements, or auditing workflow collection.