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/hautc-it/cilWrote 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/commands/hautc-it/cil/spec)<a href="https://agentmods.dev/commands/hautc-it/cil/spec"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/spec/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/commands/hautc-it/cil/spec"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/spec.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 | $0.00024 | $0.00396 |
| Opus 5.5 | $0.00010 | $0.00158 |
| Sonnet 5.5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
spec 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
/spec
Feature: $ARGUMENTS
Produce a written spec before /develop so success criteria are explicit, not inferred.
Step 1 — Clarify intent
Ask the user (or restate, if clear):
- Who is this for? (user role, system, internal)
- Why now? (problem being solved, trigger)
- What changes for the user when this exists?
If any of these are unclear, list 2–3 interpretations and ask.
Step 2 — Acceptance criteria (Given/When/Then)
Write 3–7 concrete, testable scenarios. Each one should be a single clear behavior — not a list of features.
Scenario 1: <name>
Given <starting state>
When <action>
Then <observable outcome>
Scenario 2: ...
Cover at minimum: happy path, one edge case, one failure mode.
Step 3 — Out of scope
Bullet list of related things that look in-scope but are NOT being done now. This prevents scope creep during /develop.
Step 4 — Open questions
Anything you couldn't decide alone. Flag explicitly — don't assume.
Step 5 — Persist
Store the spec for cross-session continuity:
memory_store("decision", "spec for $ARGUMENTS — <one-line summary>", ["spec", "$ARGUMENTS"])
For each acceptance criterion:
memory_store("constraint", "$ARGUMENTS must <criterion>", ["spec", "acceptance"])
Output
Print the spec, ending with:
Spec ready. Next:
/develop $ARGUMENTS.
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 · 74 lines · 24 tokens per session scan A b5aa9bfccc9f
spec is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 396 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 2026-08-31.
Other commands, from other repositories
evaluate
You are running the evaluation phase of the current Grainulator sprint. This is the honesty phase — where claims meet data.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
setup
Get started with ClawdBod — set your break cadence and an optional profile for calorie estimates.
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.