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/topos-sh/topos/claude-mdgit clone --depth 1 https://github.com/topos-sh/toposWrote 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/topos-sh/topos/claude-md)<a href="https://agentmods.dev/instructions/topos-sh/topos/claude-md"><img src="https://agentmods.dev/badge/instructions/topos-sh/topos/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 5.1 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
topos 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topos — the OSS repo (the topos CLI + the self-hostable plane + the web app)
Topos is a layer for AI agents to share behaviors within a team or organization. A behavior (a
"skill") is a bundle of files (SKILL.md + scripts + docs); the whole bundle is the unit of
trust. Two motions: distribute (publish → every subscribed agent updates silently) and
contribute (anyone proposes improvements back; review gates them).
Three programs — two in one Apache-2.0 Cargo workspace, plus a TypeScript app:
topos(bins/topos) — the client CLI an agent drives non-interactively. Full verb reference: the generateddocs/cli.md.topos-plane(bins/topos-plane) — the self-hostable vault (library + thin binary): pure byte custody, internal-network-only, ONE caller (the web app).@topos/web(web/) — the product web app (React Router 8, bun): the ONE public surface — identity, the whole directory, the/api/v1session lane, the signed-in pages,/docs. Its own toolchain and gates.
Map — read the CLAUDE.md in the folder you're working in
crates/— the five library crates:topos-types(wire DTOs),topos-core(the pure trust kernel),topos-gitstore(git object mechanics + the in-memory loose-object codec),topos-harness(the harness-adapter port + impls),plane-store(the vault's byte-custody boundary).bins/— the two Rust programs (each a lib + a thin bin).web/— the product web app.xtask/— codegen + the invariant gates (ci,check-arch, the drift gates).contracts/— the generated, committed cross-language contract (JSON-Schema, fixtures, OpenAPI).tests/— the workspace-level composed-stack e2e suites.docs/— the MDX documentation source the web app serves at/docs;docs/cli.mdis the generated CLI reference.skills/topos/— the built-intoposmeta-skill source (embedded in the binary).scripts/— installer, compose init-db/smoke, grants check, release tooling.deny.toml,RELEASING.md,docker-compose.yml+Dockerfile— supply-chain policy, the release/signing scheme, the self-host stack.
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.
- 5d ago First seen · 98 lines · 1,499 tokens per session scan A 5586e4a0d0e9
topos CLAUDE.md is an instructions file published in the GitHub repository topos-sh/topos (19 stars, last pushed 9d ago), licensed Apache-2.0. It adds 1,499 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
agentregistry copilot-instructions.md
Copilot instructions for agentregistry-dev/agentregistry, covering github copilot instructions and keeping the pr description up-to-date.
loom CLAUDE.md
Claude Code instructions for cosmix/loom, covering claude.md, project overview, build commands, architecture and source layout (loom/src/).
copilot AGENTS.md
AGENTS.md instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
autovault CLAUDE.md
Claude Code instructions for autoworks-ai/autovault, covering claude.md, project, common commands, architecture and request flow.
skills AGENTS.md
AGENTS.md instructions for tomimor/skills, covering agents.md, repo structure, adding a new own skill, own skill conventions and adding a new vendor skill set.
skilly AGENTS.md
AGENTS.md instructions for xelandernt/skilly, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.