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 commands/hautc-it/cil/testgit clone --depth 1 https://github.com/hautc-it/cilWhat 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 | $0.00034 | $0.00621 |
| Opus 5 | $0.00017 | $0.00311 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
test 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/test
Target: $ARGUMENTS
TDD assist — applies the testing skill protocol to produce a runnable test scaffold.
Step 1 — Read the target
Open the target file (or find the function across the repo). Identify:
- Public API of what's being tested (exports, function signatures, observable side effects).
- Inputs: types, ranges, optional vs required.
- Outputs: return value, thrown errors, side effects (DB writes, file writes, network).
If the target is a folder or unclear, ask which symbol to test.
Step 2 — Detect the test framework
Check package.json (devDependencies) and existing tests:
- vitest →
describe / it / expectfromvitest - jest →
describe / it / expectfromjest - node --test →
node:testrunner - pytest (Python) →
def test_*functions - go test →
func Test*(t *testing.T)
Match the existing convention. Don't introduce a new framework.
Step 3 — Generate cases (testing skill protocol)
Group into 4 sections:
- Boundary — outermost contract: function signature, public API.
- Happy path — core valid case works.
- Edge cases — empty, null, zero, max, type boundaries, unusual but valid input.
- Error cases — invalid input fails with the correct error and message.
For each case: descriptive name (returns_404_when_user_not_found, not test_user), arrange-act-assert structure, one logical assertion per it.
Step 4 — Write the file
Co-locate with existing tests (mirror their location):
- TS/JS:
src/.../__tests__/<name>.test.ts - Python:
tests/test_<name>.py
If a test file already exists, append new cases — don't overwrite.
Prefer real dependencies over mocks (testing skill rule). Mock only when crossing a network boundary.
Step 5 — Verify the scaffold runs
Run the test command (npm test, pytest, go test ./...). All new tests should fail with a meaningful error if the target doesn't exist yet, OR pass if the target is already correct.
If runner errors out (compile error, import failure), fix the test scaffold — never commit a non-running test file.
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.
- yesterday First seen · 82 lines · 34 tokens per session scan A cbb16ff1b4c6
test is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 621 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 commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.
convert-to-todowrite-tasklist-prompt
Purpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements.
security-audit
Perform a comprehensive security audit of the codebase to identify potential vulnerabilities, insecure patterns, and security best practice violations.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
session-end
I'll summarize this coding session and update the memory system with our accomplishments.