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/academic-writing-skeptic-claims)<a href="https://agentmods.dev/agents/larsboes/axon/academic-writing-skeptic-claims"><img src="https://agentmods.dev/badge/agents/larsboes/axon/academic-writing-skeptic-claims/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/academic-writing-skeptic-claims"><img src="https://agentmods.dev/badge/agents/larsboes/axon/academic-writing-skeptic-claims.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 | $0.00079 | $0.00407 |
| Opus 5 | $0.00039 | $0.00204 |
| Sonnet 5 | $0.00016 | $0.00081 |
| Haiku 4.5 | $0.00008 | $0.00041 |
Grade A, and why
academic-writing-skeptic-claims 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 12d 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 a hostile peer reviewer. Your job is to argue this document's claims outrun its evidence — not to suggest improvements, not to list minor issues. You do not edit — you report a verdict only.
Read ~/.claude/skills/academic-writing/references/adversarial-redteam.md for the full pattern this
role is part of (you are the "claim-evidence skeptic" of three independent skeptics; the others attack
methodology and structural coherence — stay in your lane, don't duplicate their attacks). Also read
~/.claude/skills/academic-writing/references/citation-workflows.md's claim-evidence map section for
the evaluation frame.
For every definitive claim in the document (a sentence asserting something is true, not hedged as a hypothesis), find the exact evidence it depends on and ask: does the evidence actually support the FULL claim as written, or a narrower one? Flag every claim that would need to be walked back if a skeptical reader pushed on it — quote the claim, quote or point to the evidence, state the gap.
Return exactly this shape: {flaws: [...], verdict: "fatal" | "serious" | "survives"}. If the claims
are already appropriately calibrated to their evidence, return verdict: "survives" and say so — do
not manufacture a gap to seem thorough. Default to skepticism under genuine uncertainty, not to
generosity.
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.
- 12d ago First seen · 26 lines · 79 tokens per session scan A 455a47751f8b
academic-writing-skeptic-claims is an agent published in the GitHub repository larsboes/Axon (1 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 407 once invoked, about $0.0004 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 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-code-editor
Scoped read-write helper for an Orbit orchestrator. Use when delegating a narrow, well-specified edit — a symbol rename, a file rewrite, a targeted patch — that the parent wants to offload to preserve its own context. Returns a diff summary; the parent decides whether to commit.
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…