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 instructions/rupaut98/ccblame/claude-mdgit clone --depth 1 https://github.com/rupaut98/ccblameWrote 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/instructions/rupaut98/ccblame/claude-md)<a href="https://agentmods.dev/instructions/rupaut98/ccblame/claude-md"><img src="https://agentmods.dev/badge/instructions/rupaut98/ccblame/claude-md.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 | $0.00569 | $0.00569 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
ccblame CLAUDE.md 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccblame
CLI ("git blame for your Claude Code spend") that parses local ~/.claude transcripts to attribute Claude Code cost per subagent, then ranks spend by subagent / workflow / project / model / day. Zero runtime deps; reads transcripts locally, never reads prompt content, never makes network calls.
Workflow
Never commit or push automatically. Stage changes, show the proposed commit message, and wait for an explicit go-ahead.
Commands
- run:
bun src/cli.ts - test:
bun test - lint:
biome check src test - typecheck:
tsc --noEmit - build:
tsdown - refresh pricing:
bun scripts/gen-pricing.ts(regeneratessrc/pricing.jsonfrom LiteLLM; also runs weekly in CI)
CI runs lint, typecheck, test, and build — keep all four green.
Modules (src/)
cli.ts— arg parsing, command dispatch, HELP textaggregate.ts— build dataset, group, spawn treeparse.ts— parse and dedup JSONL usage linescost.ts— token usage to USDdiscover.ts— find transcript/meta file pairsbrowse.ts— interactive fzf drill-downrender.ts— tables, tree, JSON outputtypes.ts,pricing.json— shared types and rate table
Invariants
Things that break correctness, privacy, or the product promise if violated silently. The full rationale and file:line citations live in .github/review-rules.md — read it before touching parsing, cost, or output.
- Privacy: readers touch only usage, model, ids, timestamps, and routing fields. Never read or emit message content, tool input, prompts, results, or summaries — in parsing or in JSON output.
- Zero runtime deps:
package.jsondependencies stays{}. UI libs are devDeps, bundled at build. - Cost reconciles: main + sub = grand total.
--topand filters trim displayed rows only, never the counts or totals. - Dedup key is
`${msgId} ${requestId}`(single space); thebetter()tie-break order is load-bearing. - Pricing is honest: an unknown model yields cost 0 plus an unpriced flag and a warning, never a silent $0.
- Spawn safety: every external binary (fzf, less, clipboard) tolerates ENOENT and degrades.
- FS reads over
~/.claudeare all guarded; recursion is symlink-safe; writes stay in a scratch dir; no network.
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 · 42 lines · 569 tokens per session scan A d186ed38fb43
ccblame CLAUDE.md is an instructions file published in the GitHub repository rupaut98/ccblame (2 stars, last pushed 11d ago), licensed MIT. It adds 569 tokens to every session, about $0.0028 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.