ax-run-capture

ax-run-capture is a skill for Claude Code, Codex from shenli/devtool-ax-kit. It costs 19 tokens per session (171 once invoked), scanned A, original, Apache-2.0.

A system for recording an agent's work with checkpoints, workspace snapshots, event histories, and receipts for outside changes. It also removes secrets from saved evidence and checks the resulting records.

In plain words
What is it for?
Use it to capture commands and trajectories, record verified external writes, handle uncertain outcomes, and track setup, execution, verification, and cleanup for external services.
Why use it?
It makes agent runs auditable and helps prevent duplicated outside changes when an earlier action has an uncertain result.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/shenli/devtool-ax-kit/ax-run-capture
Any agent
npx skills add shenli/devtool-ax-kit --skill ax-run-capture
Clone the repo
git clone --depth 1 https://github.com/shenli/devtool-ax-kit

Made for: Claude Code, Codex.

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.

agentmods badge for ax-run-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/shenli/devtool-ax-kit/ax-run-capture.svg)](https://agentmods.dev/skills/shenli/devtool-ax-kit/ax-run-capture)
Your own site
<a href="https://agentmods.dev/skills/shenli/devtool-ax-kit/ax-run-capture"><img src="https://agentmods.dev/badge/skills/shenli/devtool-ax-kit/ax-run-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00171
Opus 5 $0.00010 $0.00086
Sonnet 5 $0.00004 $0.00034
Haiku 4.5 $0.00002 $0.00017

Measured 4d ago against content hash 641a83dbca25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-run-capture 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.

skills/ax-run-capture/SKILL.md · 18 lines

What it actually says

Use the local agent_run package to capture the command, starting and ending workspace snapshots, trajectory events, and checkpoints. Record external writes only with an authoritative receipt and stable effect identity. Redact secrets before persistence and scan the resulting evidence.

When a write has an uncertain outcome, do not repeat it blindly: pin the prior receipt and replay it as a non-executing lookup. Block unrecorded writes during replay. Keep credentials out of prompts, source files, snapshots, and reports.

For external services, capture provisioning, credential delivery, execution, verification, and cleanup as separate lifecycle receipts. If a resource cannot be retrieved, record resource_unavailable and stop that trial.

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.

  1. 4d ago First seen · 18 lines · 19 tokens per session scan A 641a83dbca25

Subscribe to this mod's changes

ax-run-capture is a skill published in the GitHub repository shenli/devtool-ax-kit (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 19 tokens to every session and 171 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 2026-08-31.

Related

Other skills, from other repositories

write-docs

Authoring workflow and guardrails for writing, moving, or restructuring Coder documentation under docs/. Points at the canonical content guidelines and prose style guide, then walks research, routing, Diátaxis mode, structure, pedagogy, and validation. Counterpart to the doc-check skill, which reviews changes for…

coder/coder · 68 tokens

coder-agents-review

Use this skill when a repository already has an open pull request and you need to run the Coder Agents Review loop: request review with /coder-agents-review when needed, wait for feedback from the coder-agents-review GitHub app, fix issues, and repeat until the app comments approved.

coder/coder · 68 tokens

dogfood

Run a Coder PR dogfood instance: inspect PR context, check out the right branch or stack, start Coder with scripts/develop.sh using agent-safe dev-instance practices, validate the changed functionality with UI evidence when needed, and report findings.

coder/coder · 53 tokens

refine-plan

Iteratively refine development plans using TDD methodology. Ensures plans are clear, actionable, and include red-green-refactor cycles with proper test coverage.

coder/coder · 34 tokens

pricing

Help the user decide what to charge and how to package it: the value metric, the tiers, the free-to-paid line, and finding the actual number. Use when the user is guessing at a price, priced too cheap and can't change it, is stuck on free vs paid, or believes "developers won't pay" so never charges.

AIDevGTM/gtm-cofounder · 70 tokens

pull-requests

Guide for creating, updating, and following up on pull requests in the Coder repository. Use when asked to open a PR, update a PR, rewrite a PR description, or follow up on CI/check failures.

coder/coder · 47 tokens