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/osiris-devworks/smart-citizen/test_coverage_checkgit clone --depth 1 https://github.com/Osiris-DevWorks/smart-citizenWhat 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 | $0.00014 | $0.00784 |
| Opus 5 | $0.00007 | $0.00392 |
| Sonnet 5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
test_coverage_check 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/test_coverage_check
For every source file modified on the current branch, decide whether it should have a unit test and whether that test exists or was updated. Surface gaps; don't auto-write tests.
Severities
- Critical — non-exempt code (per the table below) with no matching test. Blocks merge in
/pull_request. - Major — existing test covers an old branch of changed logic but does not exercise the new branch.
- Minor — exempt code (workers, GUI wiring, scripts) flagged for manual attention so the user remembers to smoke-test.
Scoping the diff
git diff --name-only $(git merge-base HEAD origin/main)...HEAD
If origin/main is not the right baseline (e.g. on a release/X.Y.Z integration branch), use the integration branch as the base instead.
Coverage rules
| Area | Coverage requirement |
|---|---|
src/utils/, src/parser/, src/merger/, src/models/ |
Required. New public functions, new classes, changed branching logic need new or updated tests in tests/. |
Pure-Python helpers extracted from GUI: validate_applied_file, filter_entry_indices, markdown_to_html |
Required — these were specifically extracted so they could be tested without Qt. |
src/gui/workers.py (QThread workers) |
Exempt. Needs pytest-qt (not a dev dep). Manual smoke testing is the documented path. Flag for human attention. |
src/gui/*.py (widget layout, signal connections, MainWindow wiring) |
Exempt. Manual GUI testing only. Surface for review. |
scripts/ |
Exempt. Manual CLI exercise. Surface for review. |
Procedure
- Run the diff. Group the file list by area per the table above.
- For each non-exempt file, identify the new or changed callable (function/class). Check
tests/for a matching test (filename convention istest_<module>.py, functiontest_<callable>_<scenario>). - For changed branching logic in existing code, confirm the existing test covers the new branch — read the test to verify, don't trust the filename alone.
- Run
pytest tests/and report pass/fail with the count.
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 · 66 lines · 14 tokens per session scan A 90912c157809
test_coverage_check is a command published in the GitHub repository Osiris-DevWorks/smart-citizen (99 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 784 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.