make-agents-cheaper: Skill for Claude Code

.claude/skills/claude-trace-recovery/SKILL.md

claude-trace-recovery is a skill for Claude Code, Codex from Just-Agent/make-agents-cheaper. It costs 55 tokens per session (499 once invoked), scanned A, original, MIT.

A fallback workflow for capturing Claude Code runs as JSON when the optional claude-trace tool is unavailable or fails.

In plain words
What is it for?
Use it to capture Claude usage, cost, timing, validation, and task results, then import them into experiment files for comparison.
Why use it?
It keeps experiments running while recording which evidence is reliable. It also prevents failed runs, warm-up calls, and sensitive request data from being mishandled.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

This is Just-Agent/make-agents-cheaper's own configuration. It tells Claude Code and Codex how to work on make-agents-cheaper itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything make-agents-cheaper configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Just-Agent/make-agents-cheaper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Just-Agent/make-agents-cheaper/main/.claude/skills/claude-trace-recovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Just-Agent/make-agents-cheaper

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 claude-trace-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/just-agent/make-agents-cheaper/claude-trace-recovery/github.svg)](https://agentmods.dev/skills/just-agent/make-agents-cheaper/claude-trace-recovery)
Your own site
<a href="https://agentmods.dev/skills/just-agent/make-agents-cheaper/claude-trace-recovery"><img src="https://agentmods.dev/badge/skills/just-agent/make-agents-cheaper/claude-trace-recovery/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.

agentmods 80×15 button for claude-trace-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/just-agent/make-agents-cheaper/claude-trace-recovery"><img src="https://agentmods.dev/badge/skills/just-agent/make-agents-cheaper/claude-trace-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00499
Opus 5 $0.00028 $0.00249
Sonnet 5 $0.00011 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured 10d ago against content hash 11996619ee65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-trace-recovery 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 10d 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.

.claude/skills/claude-trace-recovery/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Trace Recovery

Purpose

Keep make-agents-cheaper experiments moving without requiring claude-trace, while preserving evidence discipline.

The default path is direct Claude JSON plus claude-json-import. Optional trace capture is only for future request-shape analysis.

Decision Flow

  1. Use the direct JSON path by default:
claude --output-format json
-> claude-json-import
-> baseline.jsonl or cache-friendly.jsonl
  1. Mark evidence strength:
  • direct JSON: usage, cost, latency, validation, and task success;
  • optional trace path: usage plus request-shape evidence;
  • no cache accounting: exploratory evidence only.
  1. Do not install or debug claude-trace unless the user explicitly asks for request-shape artifacts.

Required Rules

  • Never delete or overwrite failed or anomalous runs.
  • Keep warm-up calls out of measured results.
  • Store direct Claude JSON fallback files under runs/<experiment>/raw/claude-json/.
  • Store optional trace files under runs/<experiment>/raw/claude-trace/ only when explicitly captured.
  • Do not paste raw requests, system prompts, auth headers, or full tool outputs into reports.
  • When using direct JSON fallback, record that request/layer/tool artifacts are unavailable.
  • For ignored fixture experiments, use noninteractive permission mode only when the run is intentionally sandboxed to the fixture.

Command Details

Read references/command-shapes.md when preparing or repairing a concrete run command.

Use the project CLI commands:

  • claude-json-import for direct Claude Code JSON;
  • trace-import only for optional raw claude-trace JSONL;
  • eval, task-report, and analysis-report after normalization.

Handoff Note

After every recovery pass, write or update an evolution note under taskplan/ with:

  • that direct JSON was used;
  • raw artifact locations;
  • validation result;
  • that request-shape evidence is unavailable unless optional trace artifacts exist;
  • the next smallest safe run.

Read the full file on GitHub · 61 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 61 lines · 55 tokens per session scan A 11996619ee65

Subscribe to this mod's changes

claude-trace-recovery is a skill published in the GitHub repository Just-Agent/make-agents-cheaper (23 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 499 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens