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/nolindnaidoo/secrets-le/agents-mdgit clone --depth 1 https://github.com/nolindnaidoo/secrets-leWrote 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/nolindnaidoo/secrets-le/agents-md)<a href="https://agentmods.dev/instructions/nolindnaidoo/secrets-le/agents-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/secrets-le/agents-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 | $0.05332 | $0.05332 |
| Opus 5 | $0.02666 | $0.02666 |
| Sonnet 5 | $0.01066 | $0.01066 |
| Haiku 4.5 | $0.00533 | $0.00533 |
Grade A, and why
secrets-le 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 5d 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.
This is a copy
89% identical to regex-le AGENTS.md — 77 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Secrets-LE
Technical source of truth for this repo. README.md is the user-facing doc; this file is for anyone (human or agent) changing the code.
This repo hosts two products: the extension at the root (this document's scope) and the Rust CLI in crate/ (its own AGENTS.md + SPEC.md). The shared detection corpus lives at crate/signatures/ and crate/fixtures/; scripts/check-detection-parity.ts fails CI when this extension drifts from it.
What this is
A VS Code extension that scans the workspace for hardcoded secrets (API keys, tokens, passwords, PEM private keys, credentialed database URLs) and can replace detections in the active file with a placeholder. Detection is regex over whole file content — no parser, no network, no writes outside normal document edits.
Architecture
extension.ts activate(): createServices() -> registerCommands()
services/serviceFactory createServices(context) -> { telemetry, notifier,
statusBar, performanceMonitor }
commands/ one file per command; deps injected as a frozen bag
detect (workspace scan), sanitize (active file),
help, settings (in config/)
extraction/detectors.ts THE single pattern table (SECRET_PATTERNS) +
detectSecrets() over whole content with the d flag
extraction/heuristics.ts shared value heuristics: looksLikePlaceholder,
confidenceByLength, isJwtShaped
extraction/position.ts offset -> {line, column} via newline index (1-based)
extraction/extract.ts detectSecretsInContent, offset-based sanitizeContent,
result formatters
utils/ errors (sanitizeErrorMessage), safety (size guards),
workspaceScanner (findFiles + per-file detection),
performance (operation timing for telemetry)
ui/ notifier (window messages, gated by notificationsLevel:
all -> everything, important -> warn+error,
silent -> error only), statusBar
config/config.ts getConfiguration() snapshot; CONFIG_DEFAULTS table
types.ts shared types only — no logic
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.
- 5d ago First seen · 324 lines · 5,332 tokens per session scan A a264a7d89c6f
secrets-le AGENTS.md is an instructions file published in the GitHub repository nolindnaidoo/secrets-le (1 stars, last pushed 3d ago), licensed MIT. It adds 5,332 tokens to every session, about $0.0267 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to regex-le AGENTS.md, differing in 77 lines, and is treated as a copy.
Other instructions, from other repositories
prek AGENTS.md
AGENTS.md instructions for j178/prek, covering code quality, writing style, build and tests, github interaction and pull requests.
python-uv CLAUDE.md
Claude Code instructions for a5chin/python-uv, covering claude.md, project overview, development commands, package management and install dependencies.
pre-commit-hooks copilot-instructions.md
Copilot instructions for duolingo/pre-commit-hooks, covering development rules, architecture, build deploy, root and testing.
regex-le AGENTS.md
AGENTS.md instructions for nolindnaidoo/regex-le, covering agents.md — regex-le, what this is, architecture, code style and control flow.
regex-le CLAUDE.md
Claude Code instructions for nolindnaidoo/regex-le, covering claude.md, where to look, gates and things that will bite you.
envsync-le AGENTS.md
AGENTS.md instructions for nolindnaidoo/envsync-le, covering agents.md — envsync-le, what this is, architecture, code style and control flow.