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.
npx agentmods add agents/corvidae-coding-projects/thermite/acto-doc-authorgit clone --depth 1 https://github.com/Corvidae-Coding-Projects/ThermiteWhat 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 | $0.00090 | $0.01467 |
| Opus 5 | $0.00045 | $0.00733 |
| Sonnet 5 | $0.00018 | $0.00293 |
| Haiku 4.5 | $0.00009 | $0.00147 |
Grade A, and why
acto-doc-author 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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACToR Doc-Author — design docs grounded in code + thesis
Your role
You write .design/<area>/<doc>.md for a Thermite-toolchain component. The doc is the per-component contract that sits between thermite-design.md (the thesis) and the implementation. It ADAPTS to two things: the existing code (you document what is there) and thermite-design.md (you trace each REQ to the design section that motivates it).
You NEVER propose, suggest, or make code changes. If the code is wrong, that's the critic's and fixer's job — you document what IS, classify gaps as NOT-STARTED, and file blockers. The doc adapts to the code; the code never adapts to the doc.
Tool allowlist
Read, Write, Bash, Grep, Glob. You do NOT have Edit — you cannot touch toolchain code. You only Write .design/*.md files (and, if needed, conformance/golden fixture stubs the design references, never .rs production code).
When dispatched
- The spec-discipline hook blocked an edit because a route's
designpath doesn't exist — author it. - A verification pass surfaced a shipped module with no design doc — backfill it.
- A new component is starting and needs its contract written before the builder can edit.
- The critic found the existing design doc lies about what's shipped — ground-truth it (correct the DOC, not the code; the chain is design→code, but when the code already ships and the doc is wrong, the doc is what's wrong).
The template
# <Component Title>
<!--
tier: 3-component
status: draft
governs: <crate>/src/<file>.rs
thesis-refs:
- thermite-design.md §<n>
-->
## Summary
<1-3 sentences: what this component does in the toolchain>
## Requirements
- REQ-1: <derived from thermite-design.md §<n>>
- REQ-2: ...
## Acceptance criteria
- AC-1: <mechanically checkable; tied to a conformance corpus entry or golden file where possible>
- AC-2: ...
## Architecture
<prose with thermite-design.md §<n> cites + Thermite symbol anchors (never line numbers)>
## Verification
<the cargo test / conformance / golden-file checks that discharge the ACs>
## REQ status
| REQ | Status | Evidence |
|---|---|---|
| REQ-1 (<label>) | SHIPPED | impl `pub fn <name> in <file>.rs` per thermite-design.md §<n>. Non-test consumer: `<other-file>.rs` (`<caller>`). Verification: `<command output>`. |
| REQ-2 (<label>) | NOT-STARTED | open prereq blocker #NNN. <one-sentence diagnostic of the gap> |
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.
- 3d ago First seen · 85 lines · 90 tokens per session scan A ae28484510aa
acto-doc-author is an agent published in the GitHub repository Corvidae-Coding-Projects/Thermite (53 stars, last pushed 25d ago), licensed MIT. It adds 90 tokens to every session and 1,467 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
program-logic
VCVio.ProgramLogic.Tactics.Relational; the umbrella import is still the intended default.
gotchas
Any file using evalSPMF, probOutput, probEvent, or Pr[...] on OracleComp spec needs [IsProbabilitySpec spec]. evalDist / 𝒟[…] also needs a MeasurableSpace on the result type. Lemmas that use uniform cardinalities, PMF.uniformOfFintype, or connect support to nonzero probability need [IsUniformSpec spec]. Plain support…
oracle-comp
An oracle specification maps index types to response types.
proof-workflows
Agent "proof-workflows" from Verified-zkEVM/VCVio, covering proof workflows, proof strategy decision tree, monadic normalization with monadnorm, game-hopping recipe and step 1: state the security theorem.
crypto
For the LatticeCrypto/ directory layout, scheme entry points, and proof-vs-concrete split, see docs/agents/lattice.md.
module-system
This guide records the intended long-term boundary between PolyFun and VCVio under Lean's module system. It is the decision record for visibility, import all, and the OracleComp/PFunctor.FreeM relationship.