What is tm-marathon-config-example?

A sample project-configuration section for CLAUDE.md, a file that gives coding agents instructions about a codebase. It defines branch, approval, and automated-review settings for marathon work.

Use it as a template when configuring automated task and pull-request workflows for a repository.

It gives a project a documented starting point instead of requiring every command to guess how branches, approvals, and review bots should work.

tm-marathon-config-example — Skill for Claude Code by bjcoombs

Install

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.

Any agent

npx skills add bjcoombs/ai-native-toolkit --skill tm-marathon-config-example

Clone the repo

git clone --depth 1 https://github.com/bjcoombs/ai-native-toolkit

Made for: Claude Code.

Or install ai-native-toolkit, the plugin that ships this one along with the rest of its 19 skills, 8 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example/github.svg)](https://agentmods.dev/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example)

Your own site

<a href="https://agentmods.dev/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example"><img src="https://agentmods.dev/badge/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example"><img src="https://agentmods.dev/badge/skills/bjcoombs/ai-native-toolkit/tm-marathon-config-example.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,160 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00026	$0.01160
Opus 5.5	$0.00010	$0.00464
Sonnet 5.5	$0.00005	$0.00232
Haiku 4.5	$0.00003	$0.00116

Measured 13d ago against content hash 03804f36100c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 13d 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.

skills/tm-marathon-config-example/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 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 skills 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

Three optional per-bot fields drive pr-review-merge Ready Criterion 6 (bot re-review of the head SHA):

Re-reviews on push: yes|no - opt-in, no by default. yes means the PR is not ready until this bot has completed its pass on the current head SHA. Bots without yes are never waited on. Turn it on only for a bot that reliably re-reviews every push and whose findings you want before merge (for example an AI reviewer on AI-authored changes); leave it no for a bot that is rate-limited or often skips re-reviews, or every PR stalls for the full max wait.
Max wait for re-review: <duration> - upper bound (e.g. 10m) measured from when the head commit was pushed (its earliest check-suite creation). When Re-reviews on push: yes and this field is absent, the bound is 15m. When it expires the criterion passes with a warning naming the bot in the merge record.
Re-review check name: <check-run name> - set when the bot's pass shows up as a check run (for example a GitHub Actions reviewer job) rather than a submitted review. The criterion then reads only the check run of that name on the head SHA: in progress means keep waiting until the max wait expires; completed with conclusion success satisfies the criterion; completed with conclusion skipped means the bot does not apply to this PR, which satisfies the criterion with no warning; completed with any other conclusion (failure, cancelled, neutral, timed_out) is a settled verdict that the bot did not complete a green pass, so the criterion passes at once with a warning in the merge record. Nothing holds forever on an advisory bot.

Read the full file on GitHub · 80 lines

Changes

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.

13d ago First seen · 80 lines · 26 tokens per session scan A 03804f36100c

Subscribe to this mod's changes

tm-marathon-config-example is a skill published in the GitHub repository bjcoombs/ai-native-toolkit (32 stars, last pushed 5d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,160 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.

Claude Code Git and workflow Project management agent-skills agentic-ai ai-agents anthropic claude

fleet-orchestrator

Use when you orchestrate several workers at once (Codex or vibe sessions and Claude subagents) delivering parallel pull requests, on one machine or across several, for a human operator who does QA and merges. Covers who may write where, orchestration state that survives a reboot, restart or compaction, starting…

closedloop-ai/claude-plugins · 150 tokens

cross-repo-cache

Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…

closedloop-ai/claude-plugins · 81 tokens

tm-marathon-config-example