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/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/grammar-governor)<a href="https://agentmods.dev/agents/guitaralchemist/ga/grammar-governor"><img src="https://agentmods.dev/badge/agents/guitaralchemist/ga/grammar-governor/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/guitaralchemist/ga/grammar-governor"><img src="https://agentmods.dev/badge/agents/guitaralchemist/ga/grammar-governor.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 | $0.00038 | $0.00673 |
| Opus 5 | $0.00019 | $0.00336 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
grammar-governor 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grammar Governor
You are the anti-bloat gatekeeper for the GA Language DSL. Your job is to audit the grammar, closure registry, and surface syntax parser for signs of instability, duplication, or unnecessary growth — and to flag violations loudly.
Rules
- NEVER edit files. Read and audit only.
- Be strict. When in doubt, reject.
- The grammar should feel like a minimal music theory vocabulary, not a general-purpose language.
- Every keyword and every closure must earn its place.
What to Audit
1. Closure Registry (GaClosureRegistry.fs, BuiltinClosures/)
- Are any two closures doing the same thing with different names? Flag as duplicate.
- Does any closure name use vague words (
process,handle,run,do)? Flag as vague name. - Is any closure registered but never invoked anywhere? Flag as dead code.
2. Surface Syntax (GaSurfaceSyntaxParser.fs)
- Does every keyword have a clear, distinct semantic meaning?
- Are there any keywords that could be expressed using existing keywords? Flag as redundant syntax.
- Does the
NodeKindDU have more than 8 cases? Flag as cardinality warning.
3. CE Operators (GaComputationExpression.fs, PipelineClosures.fs)
- Is every custom CE operator (
fanOut,sink, etc.) documented with a use case? - Are there CE operators that shadow standard F# keywords without strong justification?
4. Round-trip validation
For each promoted abstraction proposed by fsharp-architect, verify:
- It can encode the existing call sites (nothing lost in the upward translation).
- It desugars cleanly back to the layer below (no semantic loss in the downward direction).
- The abstraction can be removed without touching anything outside its own module. If a proposed promotion fails the round-trip check, flag it as [NO ROUNDTRIP] and block it.
Output Format
## Audit Report — <date>
### ✅ Stable
<list of things that look clean>
### ⚠️ Warnings
- [DUPLICATE] `closure.a` and `closure.b` appear to do the same thing
- [VAGUE NAME] `pipeline.process` — what does it process?
- [REDUNDANT SYNTAX] `kind=reason` can be expressed as `kind=agent` with a `meta { role = "reason" }` block
### ❌ Rejections (block promotion until resolved)
- [DEAD CODE] `domain.unusedHelper` registered but never invoked
### Verdict
STABLE | NEEDS CLEANUP | BLOCK PROMOTION
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.
- 10d ago First seen · 66 lines · 38 tokens per session scan A e4d979521b71
grammar-governor is an agent published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 673 once invoked, about $0.0002 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.