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/flomio/passninja-cli/claude-mdgit clone --depth 1 https://github.com/flomio/passninja-cliWhat 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 | $0.00763 | $0.00763 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
passninja-cli 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
passninja-cli notes for Claude Code
What this repo is
The Go CLI for the PassNinja REST API. Module path
github.com/flomio/passninja-cli. Cobra + Viper, Go 1.22+. Distributed via
Homebrew from the flomio/homebrew-passninja tap.
Predecessor was a TypeScript NFC scanner (Webpack 4 + Jest). That source is
preserved on the legacy/nfc-scanner tag — see git show legacy/nfc-scanner
if you ever need to read it. Do not resurrect it.
Top-level layout
cmd/ — one file per Cobra command. cmd/root.go wires the API client
onto cmd.Context() in PersistentPreRunE.
pkg/
api/ — HTTP client + per-resource methods (pass templates, passes,
webhooks). do() handles retry on 429/5xx.
auth/ — ~/.passninja-auth.json read/write + interactive prompt.
config/ — Viper bootstrap; env var binding (PASSNINJA_*).
output/ — Mode (table | json | plaintext); PrintJSON / PrintTable;
Error/Success/Info/Warn split between stderr/stdout.
utils/ — ids.go (ptk_/aid_ helpers), input.go (--field k=v parsing).
.github/workflows/release.yml — tag-triggered build + tap bump.
When you add a new endpoint to passninja-site
- Add the resource method to
pkg/api/<resource>.go. Usec.do(ctx, method, path, body, &out). - Add a command file in
cmd/<resource>_<verb>.go. Mount it under the parent resource command in that file'sinit(). - Add a row helper in
pkg/output/tables.goif the response is a list. - Update the command tree in
README.md.
Output rules
- Errors go to stderr (
output.Error), payloads to stdout. This lets scripts pipepassninja … --jsonstraight tojqwithout filtering. - The default is
table.--jsonand--plaintextare mutually exclusive; if both are passed,--jsonwins (more useful for downstream parsing). webhook createprints the bearer token to stdout once. In--jsonmode it sits inside the response object; in table/plaintext it gets a separateoutput.Warn("Save this token now — it will not be shown again.")line.
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.
- yesterday First seen · 63 lines · 763 tokens per session scan A c5849158a846
passninja-cli CLAUDE.md is an instructions file published in the GitHub repository flomio/passninja-cli (0 stars, last pushed 1mo ago), licensed MIT. It adds 763 tokens to every session, about $0.0038 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.