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/mmacpherson/tenforty/graph-qagit clone --depth 1 https://github.com/mmacpherson/tenfortyWrote 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/mmacpherson/tenforty/graph-qa)<a href="https://agentmods.dev/commands/mmacpherson/tenforty/graph-qa"><img src="https://agentmods.dev/badge/commands/mmacpherson/tenforty/graph-qa.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00458 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
graph-qa 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 3d 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
Run complete quality assurance checks for graph backend (Haskell + Rust) before committing.
Prerequisites:
- Changes involve Haskell code in
tenforty-spec/or state tax forms - Working on graph backend or Rust code in
crates/tenforty-graph/
- Check
git statusto understand current state - Format Haskell code:
make spec-fmt- May alphabetize imports or reformat code
- Note any formatting changes for staging
- Lint Haskell code:
make spec-lint-strict- Should report "No hints"
- Fix any hints before proceeding
- Generate JSON graphs:
make spec-graphs- Watch for compilation errors or warnings
- Note any unexpected changes to existing forms
- Sync graphs to Python:
make forms-sync- Reports number of graphs synced
- Rebuild Rust extension:
make env-full- Critical: keeps
.soin sync with Rust source - Prevents test failures from out-of-date extension
- Critical: keeps
- Run pre-commit hooks:
make run-hooks- Must pass before committing
- Re-stage files if auto-fixed
- Run test suite:
uv run pytest tests/ -q --tb=line- Expected: 203+ passed, some skipped/xfailed
- All graph tests must pass
- Review staging with
git status- Check for unexpected changes (modified forms, etc.)
- Remove orphaned JSONs without Haskell sources if any
- Stage formatting changes from step 1 if needed
- For state-specific work, run focused test:
uv run pytest tests/regression_test.py -k "WI" -v(replace state)
- Report results and any files needing staging decisions
Common issues:
- If
graphlib_link_year_test.pyfails:.soout of sync, runmake env-full - If unexpected JSON changes: review with
git diff, decide to include/separate/discard - If untracked JSON files appear: likely stale, safe to remove
Always prefer make targets over running commands directly.
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.
- 3d ago First seen · 42 lines · 0 tokens per session scan A 3f52ce71b7e8
graph-qa is a command published in the GitHub repository mmacpherson/tenforty (84 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 tokens. 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.