Borrowing it
Nothing to install: this file belongs to tugraskan/Tamandua. 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/tugraskan/Tamandua/main/CLAUDE.mdgit clone --depth 1 https://github.com/tugraskan/TamanduaWrote 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/tugraskan/tamandua/claude-md)<a href="https://agentmods.dev/instructions/tugraskan/tamandua/claude-md"><img src="https://agentmods.dev/badge/instructions/tugraskan/tamandua/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/tugraskan/tamandua/claude-md"><img src="https://agentmods.dev/badge/instructions/tugraskan/tamandua/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 | $0.00711 | $0.00711 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
Tamandua 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tamandua
Read docs/status.md before anything else — it is the one-page map of what
is current, what is measured, and what is open.
What this is
A facts-only index of SWAT+ Fortran source -- procedures with locations, the call graph, file I/O with unit numbers, variable assignments by field path, loop headers with their index variables, derived types with the units and meaning the source documents inline. Everything is static analysis; nothing is written by a model.
Two deliveries over one implementation:
tamandua/mcp/server.py-- 14 read-only toolstamandua/index/-- writesSWATPLUS_INDEX.mdinto a checkout, plus a pointer in each assistant's instruction file
tamandua/output/reader.py answers the one thing no index can: what
a run's numbers actually did.
Building needs the parser in swatplus-reference-corpus; serving does not.
swatplus-build writes swatplus-facts.json, which the server answers from
with neither the parser nor a SWAT+ checkout present (docs/decisions.md D-8).
Working here
export SWATPLUS_SOURCE=/path/to/swatplus
export SWATPLUS_REFERENCE_CORPUS=/path/to/swatplus-reference-corpus # the parser
pip install -e ".[dev]"
python -m pytest -q # 151 pass, 9 skipped (128/32 without the parser)
swatplus-build from inside a SWAT+ checkout writes the facts file and
nothing else; --markdown adds the greppable rendering and the instruction
pointers, for a tool that cannot run a server. A running server checks an
explicit source tree or --facts file before every request and refreshes only
after it changes. The package-bundled release snapshot remains static.
Conventions
- Facts only. If a model wrote it, it does not go in the index. Only swatplus-reference-corpus's schema scanner is used; its 1,095 generated prose pages are deliberately unused. The same rule retired its predecessor's overlays, where an audit found ~1 in 5 AI-generated equation mappings pointed at the wrong routine.
- Every claim carries its evidence. A row without a file and line is not worth shipping.
- Measure before concluding. Findings live in
docs/*_experiment.md, each with the script that produced them and its caveats. Where a later measurement overturned an earlier conclusion, the earlier write-up goes --docs/status.mdrecords what survived. - Eight defects in this work were found by ordinary use and none by any harness. Prefer running the thing over reasoning about it.
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.
- 8d ago First seen · 66 lines · 711 tokens per session scan A 2c9751dd780b
Tamandua CLAUDE.md is an instructions file published in the GitHub repository tugraskan/Tamandua (0 stars, last pushed 11d ago), licensed MIT. It adds 711 tokens to every session, about $0.0036 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.