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/davetashner/stringer/claude-mdgit clone --depth 1 https://github.com/davetashner/stringerWhat 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 | $0.00923 | $0.00923 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
stringer 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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Stringer
Git Workflow
- Always use PRs. Never push directly to
main. Create a feature branch, commit, push, and open a PR withgh pr create. - Branch naming:
<type>/<short-description>(e.g.,feat/todo-collector,fix/config-loading) - Commit messages: conventional commits format (
feat:,fix:,chore:,docs:,test:) - DCO sign-off required. Always use
git commit -s(or--signoff) so every commit includes aSigned-off-byline. CI will reject commits without it. - Check for existing open PRs with
gh pr listbefore creating new ones to avoid duplicates - Prefer adding commits to an existing open PR for related work
Secret Safety
- Never commit secrets. The pre-commit hook runs
gitleaksautomatically. - If you get a gitleaks error, fix the issue — do not bypass with
--no-verify. - New clones must run:
git config core.hooksPath .githooks
Beads Backlog
- Find work:
bd ready --json - Before starting: claim an issue or create one with
bd create - Reference issue ID in commits:
feat: add scanner [stringer-bsf] - After PR merge:
bd close <id> --reason "Completed in PR #N"
Decision Records
- When a task involves choosing between approaches (libraries, patterns, formats, trade-offs), write a decision record before implementing.
- Create
docs/decisions/NNN-short-title.mdusing the template in AGENTS.md. - Set status to
Proposed— do not implement until a developer accepts the decision. - Reference the beads issue ID in the record's Context field.
Build & Test
go build -o stringer ./cmd/stringer
go test -race ./...
golangci-lint run ./...
Current Focus
- L1 Language Support Expansion (
stringer-043) — complete; PHP, Swift, Scala, Elixir landed in PR #310. - Deep-scan follow-ups:
ds1/ds2/ds3closed in PR #326 (bounded registry reads, ctx cancellation in dephealth check loops, L1 registry test coverage).ds4(configurable registry timeout) deliberately deferred as low-value;ds5open if applicable — checkbd ready. - Quick wins: P3/P4 unblocked tasks — run
bd ready
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 · 73 lines · 923 tokens per session scan A f99499f49393
stringer CLAUDE.md is an instructions file published in the GitHub repository davetashner/stringer (53 stars, last pushed 4d ago), licensed MIT. It adds 923 tokens to every session, about $0.0046 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
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.
icloud-reminders-mcp CLAUDE.md
Claude Code instructions for Lingnik/icloud-reminders-mcp, covering icloud-reminders-mcp — project conventions, backlog: github issues, always, secrets, architecture and testing.