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/modeled-information-format/mnemonic/test-reportgit clone --depth 1 https://github.com/modeled-information-format/mnemonicWhat 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 | $0.00010 | $0.00778 |
| Opus 5 | $0.00005 | $0.00389 |
| Sonnet 5 | $0.00002 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
test-report 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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Test Report
Create a comprehensive report of test execution results.
Report Generation
if [[ ! -f ".claude/test-state.json" ]]; then
echo "No test results found. Run /run-tests first."
exit 1
fi
"./.claude/tests/runner.sh" report {{#if format}}--format {{format}}{{/if}}
"./.claude/tests/runner.sh" report --format {{format}} > {{output}}
Otherwise, display in conversation.
Report Formats
Markdown (default)
# Test Execution Report
**Generated:** 2026-01-24T15:30:00Z
## Summary
| Status | Count | Percentage |
|--------|-------|------------|
| ✅ Passed | 18 | 90.0% |
| ❌ Failed | 1 | 5.0% |
| ⏭️ Skipped | 1 | 5.0% |
| **Total** | **20** | **100%** |
## Failed Tests
### cmd_search_empty
**Category:** commands
**Description:** Search with no results returns empty message
**Expected:**
- contains: "no results"
**Actual Response:**
> Found 0 matches for query
**Failure:** Missing 'no results'
## Passed Tests
<details>
<summary>18 tests passed (click to expand)</summary>
- ✅ smoke_basic
- ✅ cmd_capture_basic
- ✅ cmd_recall_basic
...
</details>
JSON
{
"generated_at": "2026-01-24T15:30:00Z",
"summary": {
"total": 20,
"passed": 18,
"failed": 1,
"skipped": 1,
"pass_rate": 0.90
},
"results": [...],
"metadata": {
"filters": {
"category": null,
"tag": null
},
"test_file": ".claude/tests/tests.yaml",
"runner_version": "1.0.0"
}
}
HTML
Generates styled HTML with:
- Color-coded status badges
- Collapsible sections
- Syntax highlighting for responses
- Print-friendly styling
CI Integration
For CI/CD pipelines, use JSON format and check exit code:
./.claude/tests/runner.sh report --format json > test-results.json
# Check for failures
failures=$(jq '.summary.failed' test-results.json)
if [[ "$failures" -gt 0 ]]; then
echo "Tests failed: $failures"
exit 1
fi
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.
- 2d ago First seen · 149 lines · 10 tokens per session scan A 2f3ae46a0446
test-report is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 778 once invoked, about $0.0001 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 commands, from other repositories
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
wiring-check
End-of-task wiring gate — verify every change is connected end-to-end across kipi plugins, hooks, MCP tools, agents, bus files, canonical, and rules. Nothing dangling.
issue-closeout
Triage Codex findings via per-finding dispositions, record findingstriaged, close the active issue.
prd-personas
Run the Skeptic persona session against the active draft PRD.
prd-triage
Triage pending findings on the active PRD.
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.