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/benjamin-bader/stiletto/claude-mdgit clone --depth 1 https://github.com/benjamin-bader/stilettoWrote 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/benjamin-bader/stiletto/claude-md)<a href="https://agentmods.dev/instructions/benjamin-bader/stiletto/claude-md"><img src="https://agentmods.dev/badge/instructions/benjamin-bader/stiletto/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 | $0.00977 | $0.00977 |
| Opus 5 | $0.00489 | $0.00489 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
stiletto 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 6d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stiletto — contributor & agent guide
Stiletto is a compile-time dependency injector for .NET, ported from Square's
Dagger. The core is a Roslyn source generator (src/Stiletto.Generator) that
emits binding code at build time; src/Stiletto is the runtime library that
ships alongside it in a single NuGet package.
Commit messages: Conventional Commits (required)
Releases are automated with release-please,
which reads commit history to decide the next version and to build the
changelog. That only works if commits follow the
Conventional Commits format, so every
commit that lands on master must be conventional. PRs are squash-merged, so
in practice it's the PR title that has to conform — and the
Lint PR title workflow (.github/workflows/pr-title.yml) enforces it as a
status check.
Format:
<type>[optional scope][!]: <description>
[optional body]
[optional footer(s)]
Common types and how they affect the version:
| Type | Meaning | Version bump |
|---|---|---|
feat |
A new feature | minor |
fix |
A bug fix | patch |
perf |
A performance improvement | patch |
docs |
Documentation only | none |
refactor |
Code change that neither fixes a bug nor adds a feature | none |
test |
Adding or fixing tests | none |
build |
Build system, packaging, or dependency changes | none |
ci |
CI configuration changes | none |
chore |
Anything else not user-facing | none |
Breaking changes
Signal a breaking change either with a ! after the type/scope or with a
BREAKING CHANGE: footer. Either one triggers a major bump.
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.
- 6d ago First seen · 104 lines · 977 tokens per session scan A 0c78a3bb9ed9
stiletto CLAUDE.md is an instructions file published in the GitHub repository benjamin-bader/stiletto (43 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 977 tokens to every session, about $0.0049 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
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
loopx AGENTS.md
AGENTS.md instructions for huangruiteng/loopx, covering agent instructions, commit and pr hygiene, worktree and pr gate, dco sign-off and release contributor attribution.
relay AGENTS.md
AGENTS.md instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
uview-plus AGENTS.md
AGENTS.md instructions for ijry/uview-plus, covering agents, 提交规范, 发布规范 and uview-plus说明.
agentistics AGENTS.md
AGENTS.md instructions for blpsoares/agentistics, covering before starting implementation work, opening a pr, merging: squash a feature, merge a release, documentation and scope discipline.
cool-test-mcp AGENTS.md
AGENTS.md instructions for CoolTea001/cool-test-mcp, covering agents, commit rules, release & tag rules and documentation & test sync.