Borrowing it
Nothing to install: this file belongs to hansipie/ecotokens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hansipie/ecotokens/master/CLAUDE.mdgit clone --depth 1 https://github.com/hansipie/ecotokensWrote 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/hansipie/ecotokens/claude-md)<a href="https://agentmods.dev/instructions/hansipie/ecotokens/claude-md"><img src="https://agentmods.dev/badge/instructions/hansipie/ecotokens/claude-md/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.
<a href="https://agentmods.dev/instructions/hansipie/ecotokens/claude-md"><img src="https://agentmods.dev/badge/instructions/hansipie/ecotokens/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01663 | $0.01663 |
| Opus 5.5 | $0.00665 | $0.00665 |
| Sonnet 5.5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
ecotokens 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ecotokens Development Guidelines
Auto-generated from all feature plans. Last updated: 2026-10-17
Active Technologies
- Rust stable ≥ 1.75 + tantivy 0.22 (index read), similar 2.x (diff/similarity ratio), clap 4 (CLI), rmcp (MCP server), serde/serde_json (serialisation) (002-duplicate-detection)
- Tantivy on-disk index (read-only for this feature); no new storage introduced (002-duplicate-detection)
- Rust stable ≥ 1.75 (no nightly) + serde_json (parsing JSON stdin/stdout), clap 4 (nouvelle sous-commande), tantivy 0.22 (lookup index pour Read), existing filter modules (008-posttooluse-native-tools)
- JSONL existant (
~/.config/ecotokens/metrics.jsonl) — extension par nouveau champhook_typeavec#[serde(default)](008-posttooluse-native-tools) - Rust stable ≥ 1.75 (no nightly) + tantivy 0.22 (BM25), hnsw_rs 0.3.x (ANN index), candle (embedding), tree-sitter 0.24 (chunking), rmcp (MCP server) (009-semantic-search-embeddings)
- Index tantivy sur disque +
hnsw_index.bin(bincode) +hnsw_meta.json(009-semantic-search-embeddings) - Rust stable ≥ 1.75, edition 2021 + no new crates — reuses reqwest 0.12 (blocking), similar 2 (diff), clap 4, rmcp 1 (010-local-text-rewrite)
- Existing SQLite metrics store + plain-text diff files in a configurable directory (010-local-text-rewrite)
- Optional TypeSafe Jev judgments via
src/jev/(HTTPS, reqwest blocking;jevfeature) — no new crates; every use falls back to the existing heuristic - Rust stable ≥ 1.75 (no nightly), edition 2021 + no new crates — reuses clap 4 (subcommands), serde/serde_json (hook I/O, transcript lines), chrono, dirs, rusqlite and
masking::patterns::mask(011-session-handoff) - Plain Markdown files under
~/.config/ecotokens/handoff/plus per-session JSON records; small SQLite table for injection statistics (011-session-handoff) - Rust stable ≥ 1.75 (no nightly), edition 2021 + existing only:
clap4 (subcommands),serde/serde_json,toml1 (policy files),globset0.4 (path patterns),rusqlite0.31 (router.db),chrono,dirs,regex; internal:jev(Question/Answers),handoff(store, format, transcript),masking::patterns::mask. No new crates. (012-policy-based-router) ~/.config/ecotokens/router.db(additive columns onrouter_decisions, newrouter_outcomestable); user settings JSON gains list/flag fields; new optional~/.config/ecotokens/router_rules.toml; dossiers as Markdown under the existing handoff directory. No project file is ever written. (012-policy-based-router)
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.
- 9d ago Changed · +2 lines · +256 tokens per session 547932aabd75
- 23d ago Changed · +2 lines · +88 tokens per session 91a79d0b5a4f
- 1mo ago Changed · +3 lines · +119 tokens per session ef9a9c3f023a
- 1mo ago First seen · 68 lines · 1,200 tokens per session scan A 3d7a51030631
ecotokens CLAUDE.md is an instructions file published in the GitHub repository hansipie/ecotokens (21 stars, last pushed 4d ago), licensed MIT. It adds 1,663 tokens to every session, about $0.0067 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 2026-08-30.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.