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/7df-lab/devo/agents-mdgit clone --depth 1 https://github.com/7df-lab/devoWhat 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 | $0.01071 | $0.01071 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
devo AGENTS.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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rust
This repository is a Rust-based coding agent, currently called devo.
- All crate names use the
devo-prefix. For instance, the crate in thecoredirectory is nameddevo-core. - When using
format!, inline variables directly inside{}whenever possible. - Always collapse nested
ifstatements according to https://rust-lang.github.io/rust-clippy/master/index.html#collapsible_if - Inline
format!arguments whenever possible, following https://rust-lang.github.io/rust-clippy/master/index.html#uninlined_format_args - Prefer method references instead of closures where applicable, per https://rust-lang.github.io/rust-clippy/master/index.html#redundant_closure_for_method_calls
- Avoid using
boolor unclearOptionparameters that lead to ambiguous calls likefoo(false)orbar(None). Instead, use enums, clearly named methods, newtypes, or other idiomatic Rust patterns that improve readability at the callsite. - If such API changes are not feasible and positional literals must still be used, follow the
argument_comment_lintrule:- Add an exact
/*param_name*/comment before unclear positional literals (e.g.,None, booleans, numeric values). - Do not include these comments for string or character literals unless they genuinely improve clarity, as these are exempt.
- The comment must exactly match the parameter name in the function signature.
- Add an exact
- Make
matchexpressions exhaustive whenever possible, avoiding wildcard arms. - Any newly introduced traits must include documentation explaining their purpose and how implementations should behave.
- In tests, favor comparing full objects rather than asserting on individual fields.
- If an API is added or modified, update the relevant documentation in the
docs/directory when necessary. - Avoid introducing small helper functions that are only used once.
- Keep modules reasonably sized:
- Prefer creating new modules instead of expanding existing ones.
- Aim to keep modules under 500 lines of code, excluding tests.
- If a file grows beyond ~800 lines, place new functionality in a separate module unless there is a strong, documented justification not to.
- When running Rust-related commands (e.g.,
just fixorcargo test), allow them to complete without interruption, do not try to kill them using the PID. Slow execution due to Rust’s locking behavior is expected. - Agent can not apply patch to a file more than 800 lines, cause windows patch length limit, agent would failed to apply patch.
- Do not introduce trivial wrapper functions — call the underlying function directly unless reuse or abstraction is clearly justified.
- Exclude the target folder when using glob or grep, since it contains a large number of Rust build artifacts.
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.
- 2d ago First seen · 52 lines · 1,071 tokens per session scan A 947d3d56b152
devo AGENTS.md is an instructions file published in the GitHub repository 7df-lab/devo (317 stars, last pushed 2d ago), licensed MIT. It adds 1,071 tokens to every session, about $0.0054 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
dsh-TUI AGENTS.md
Instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
Tianshu-harness CLAUDE.md
Instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
cocode AGENTS.md
Instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.
peri CLAUDE.md
Instructions for KonghaYao/peri, covering claude.md — perihelion, 先读什么, 跨仓库契约, 任务路由 and 代码定位.
Whale AGENTS.md
AGENTS.md instructions for usewhale/Whale, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.