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/bjcoombs/ai-native-toolkit/tm-marathon-config-examplegit clone --depth 1 https://github.com/bjcoombs/ai-native-toolkitWrote 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/bjcoombs/ai-native-toolkit/tm-marathon-config-example)<a href="https://agentmods.dev/commands/bjcoombs/ai-native-toolkit/tm-marathon-config-example"><img src="https://agentmods.dev/badge/commands/bjcoombs/ai-native-toolkit/tm-marathon-config-example.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 | $0.00026 | $0.00657 |
| Opus 5 | $0.00013 | $0.00329 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
tm-marathon-config-example 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 4d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marathon Configuration Example
Copy the ## Marathon Configuration section below into your project's CLAUDE.md file.
The /tm and /issues commands read this section to configure marathon mode for your specific codebase.
If this section is missing, /tm uses these defaults:
- Base branch:
main - Required approvals: 1
- No bot reviewer rules
- No retro log
Marathon Configuration
Project-specific settings for /tm marathon mode.
Branch and Merge
- Base branch:
main - PR target branch:
main - Required approvals: 1 (minimum for auto-merge)
- Markdown-only PR approvals: 1
Bot Reviewers
CodeRabbit (coderabbitai[bot]):
- Fix code and push. CodeRabbit re-reviews automatically and resolves its own threads.
- NEVER reply in CodeRabbit threads - CodeRabbit ignores replies from other bots.
- If
request_changes_workflowis enabled: CodeRabbit submits CHANGES_REQUESTED reviews that GitHub does not auto-dismiss on re-review. Every PR needs stale bot CR dismissal before merging.
claude[bot] (claude[bot]):
- Resolve threads via GraphQL after addressing the feedback.
Human reviewers:
- Fix code, reply inline, @mention reviewer. Do NOT resolve human threads - let the reviewer confirm.
CI Patterns
- Known flaky tests: (list any tests that fail intermittently on CI but are not real failures)
- Non-blocking checks: (list checks that are informational only, not merge gates - e.g., codecov/patch, Trivy scans)
- Pre-existing failures: (list any tests that are currently broken on the base branch)
- Slow checks: (list checks that routinely take 10+ min so teammates know to expect delays)
GitHub Issues (for /issues)
- Agent-ready label:
agent-ready(opt-in label that makes an issue marathon-eligible) - Needs-triage label:
needs-triage(applied with a clarifying-question comment) - In-progress label:
in-progress(applied when a teammate starts an issue) - Issue exclude labels: (none — e.g.
discussion,wontfix,questionto skip during triage)
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.
- 4d ago First seen · 70 lines · 26 tokens per session scan A 62b0ae0aa9a4
tm-marathon-config-example is a command published in the GitHub repository bjcoombs/ai-native-toolkit (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 657 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
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.