rev_harness_public / rust-skills-knowledge-pack
AGENTS.md0 starsChanged 3 months agoApache-2.0View on GitHub
Use rust-skills-master.md as the single source of truth, SKILL.md as the compact skill entrypoint, and rust-skills-sources.md as the source registry. For implementation details, load the relevant file under references/. Hard rules: - Do not implement unbounded concurrency, unbounded channels, request-per-client construction, callback allocations, lock-held awaits, or unchecked crypto nonce/key reuse. - Run cargo audit, cargo deny check, cargo tree -e features, tests, and benchmarks when dependency or hot-path changes are made. - For QUIC/HPKE/TLS/crypto, verify transitive advisories in Cargo.lock, not…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository78 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/go-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .agents/skills/rust-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .agents/skills/typescript-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .claude/skills/go-skills-knowledge-pack/AGENTS.mdAGENTS.md
- .claude/skills/typescript-skills-knowledge-pack/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/00-general.mdcCursor rule
- .cursor/rules/revharness-critical.mdcCursor rule
- .cursor/rules/revharness-detailed.mdcCursor rule
- auto-orchestratorSkill
- baseline-protectionSkill
- client-distribution-readinessSkill
- cloudflare-deploy-guardSkill
- codex-app-server-guardSkill
- codex-app-server-product-integrationSkill
- codex-callerSkill
- context-compactorSkill
- cursor-callerSkill
- delegated-development-disciplineSkill
- deploy-command-disciplineSkill
- design-principlesSkill
- development-constitutionSkill
- development-junk-cleanupSkill
- go-skills-knowledge-packSkill
- harness-official-docs-updateSkill
- naming-normalization-guardSkill
- orchestrator-bootstrapSkill
- payload-cms-deploy-guardSkill
- production-function-implementerSkill
- research-handoffSkill
- rev-harness-lifecycleSkill
- review-workflowSkill
- root-cause-first-disciplineSkill
- rust-skills-knowledge-packSkill
- scope-guardSkill
- self-growth-proposal-triageSkill
- shared-client-wrapper-safetySkill
- slice-designerSkill
- staff-code-reviewerSkill
- structured-mentorSkill
- supabase-deploy-guardSkill
- system-plannerSkill
- typescript-skills-knowledge-packSkill
- auto-orchestratorSkill
- baseline-protectionSkill
- client-distribution-readinessSkill
- cloudflare-deploy-guardSkill
- codex-app-server-guardSkill
- codex-app-server-product-integrationSkill
- codex-callerSkill
- context-compactorSkill
- cursor-callerSkill
- delegated-development-disciplineSkill
- deploy-command-disciplineSkill
- design-principlesSkill
- development-constitutionSkill
- development-junk-cleanupSkill
- go-skills-knowledge-packSkill
- harness-official-docs-updateSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Use rust-skills-master.md as the single source of truth, SKILL.md as the compact skill entrypoint, and rust-skills-sources.md as the source …
- Distinctive: line 6
Do not implement unbounded concurrency, unbounded channels, request-per-client construction, callback allocations, lock-held awaits, or …
- Very specific: line 7
Run cargo audit, cargo deny check, cargo tree -e features, tests, and benchmarks when dependency or hot-path changes are made.
- Distinctive: line 9
Treat high-load sending and private communication as authorized, audited, rate-limited, legally compliant systems only.
- Very specific: line 14
When browser automation is required, prefer chromiumoxide only for authorized JS-rendered pages, SPA form verification, screenshots, and QA.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
RustSkills Repository Agent Instructions
Use rust-skills-master.md as the single source of truth, SKILL.md as the compact skill entrypoint, and rust-skills-sources.md as the source registry. For implementation details, load the relevant file under references/.
Hard rules:
- Do not implement unbounded concurrency, unbounded channels, request-per-client construction, callback allocations, lock-held awaits, or unchecked crypto nonce/key reuse.
- Run
cargo audit,cargo deny check,cargo tree -e features, tests, and benchmarks when dependency or hot-path changes are made. - For QUIC/HPKE/TLS/crypto, verify transitive advisories in
Cargo.lock, not only top-level crate versions. - Treat high-load sending and private communication as authorized, audited, rate-limited, legally compliant systems only.
Browser Automation/CDP
When browser automation is required, prefer chromiumoxide only for authorized JS-rendered pages, SPA form verification, screenshots, and QA. Static HTML should remain reqwest + scraper. Do not add stealth or anti-bot bypass workflows as standard implementation guidance. Browser processes must be pooled, bounded, timeout-protected, and kill-switchable.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

