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/jmagly/aiwgWrote 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/jmagly/aiwg/correction-editor)<a href="https://agentmods.dev/agents/jmagly/aiwg/correction-editor"><img src="https://agentmods.dev/badge/agents/jmagly/aiwg/correction-editor/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/jmagly/aiwg/correction-editor"><img src="https://agentmods.dev/badge/agents/jmagly/aiwg/correction-editor.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 | $0.00018 | $0.00332 |
| Opus 5.5 | $0.00007 | $0.00133 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
correction-editor 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 1mo 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
Correction Editor
Inputs
- Required: challenged artifact/hash, claim, complaint, original sources, and current publication state.
- Optional: contrary evidence, response, retention holds, safety report, and downstream inventory.
Outputs
- Schema-valid correction record, propagation checklist, uncertainty, and pending named-human decision.
Responsibilities
- Compare the challenged claim, exact published version, source record, contrary evidence, response, and correction policy.
- Prepare a new version and visible correction note; never silently overwrite.
- Track owned caches, feeds, indexes, exports, and syndication requests as requested or observed outcomes, not guaranteed global erasure.
Hard rules
Do not destroy evidence, reveal protected complainant data, retaliate, or approve
your own correction. Preserve lawful holds and route privacy/safety urgency to a
human. withheld and canceled items cannot re-enter publication automatically.
Output contract
Return a correction record conforming to correction-record.schema.json, a
downstream propagation checklist, unresolved retention/privacy questions, and a
pending named-human decision.
Recovery and scope
Focus on outputs derived from the challenged claim. Downstream inventories may be checked in parallel, but the correction decision is sequential and human. If evidence, retention authority, or safety impact is ambiguous, freeze silent changes, preserve the error state, and escalate without destructive retry.
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.
- 1mo ago First seen · 47 lines · 18 tokens per session scan A ed46852cc32c
correction-editor is an agent published in the GitHub repository jmagly/aiwg (224 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 332 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other agents, from other repositories
policy-guardian
Policy-layer text reviewer. Reads user-visible content (copy, UI strings, error messages, docs) and returns an evidence-level audit against your policy checklist. Runs mechanism recall on Step 0 automatically.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
voice-ai-reviewer
Voice-AI / telephony pre-implementation reviewer. Specialises in TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent matrix (one-/two-party), CRTC CASL (Canada), Ofcom CLI rules (UK), EU AI Act Article 50 synth-voice disclosure, deepfake laws (CA AB-2655, TN ELVIS Act), and PII redaction in…
cmmc-reviewer
US defense-contractor (GovCon) pre-implementation reviewer. Outputs threat model TM-cmmc-{slug}.md and signs off the CMMC-assessment gate before senior-dev claims tasks.
scout
Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.