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/string-le/agents-mdgit clone --depth 1 https://github.com/nolindnaidoo/string-leWhat 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 | $0.05317 | $0.05317 |
| Opus 5 | $0.02658 | $0.02658 |
| Sonnet 5 | $0.01063 | $0.01063 |
| Haiku 4.5 | $0.00532 | $0.00532 |
Grade A, and why
string-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 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.
This is a copy
88% identical to regex-le AGENTS.md — 72 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Strings-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 extraction corpus lives at crate/fixtures/; scripts/check-extraction-parity.ts fails CI when this extension drifts from it.
scripts/check-differential.ts is the second half of that guard: it drives the shared extract_strings MCP tool on both servers — this one and the crate's — over generated documents, and requires byte-identical answers. The corpus pins the cases somebody thought of; that pins the ones nobody did. Scope is the shared tool only. The two surfaces are meant to differ — this one is IDE-first, for one open buffer; the CLI is terminal-first, for trees, exit codes and pipes — so the walk, --strict, --values and --multiline are the crate's alone and are never held against this side.
What this is
A VS Code extension that extracts string values from the active document (JSON, YAML, CSV, TOML, INI, dotenv — anything else falls back to a quoted-string scan) into a results editor, with dedupe/sort post-processing and a streaming mode for large CSVs. No network access, no filesystem writes.
Architecture
extension.ts activate(): create telemetry/notifier/statusBar -> registerAllCommands()
commands/ one file per command; deps injected as a frozen bag
(extract, dedupe, sort, toggleCsvStreaming, help;
postProcessHelper shares new-file-vs-in-place output)
extraction/extract.ts dispatcher: fileType -> extractor (unknown -> fallback)
extraction/collect.ts THE shared value-collection heuristics for parsed formats
extraction/formats/*.ts one extractor per format:
json (JSON.parse), yaml (js-yaml loadAll),
toml (@iarna/toml), ini (ini), csv (csv-parse,
+ streamCsvStrings + readCsvHeader), dotenv
(line-based), fallback (quoted-string regex)
ui/ notifier (window messages, gated by notificationsLevel:
all -> everything, important -> warn+error, silent -> error only;
error/warn text sanitized), statusBar, prompts
(file-type picker, CSV column selection), largeOutput dialogs
providers/codeActions "Extract strings" quick fix for supported languages
config/config.ts readConfig() snapshot; CONFIG_DEFAULTS table
utils/ errors (sanitizeErrorMessage), filename (.env detection), text (dedupe/sort)
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.
- 2d ago First seen · 321 lines · 5,317 tokens per session scan A 57f1e875b5fc
string-le AGENTS.md is an instructions file published in the GitHub repository nolindnaidoo/string-le (1 stars, last pushed 7d ago), licensed MIT. It adds 5,317 tokens to every session, about $0.0266 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to regex-le AGENTS.md, differing in 72 lines, and is treated as a copy.
Other instructions, from other repositories
varlock copilot-instructions.md
Instructions for dmno-dev/varlock, covering copilot pr code review (security), security checklist (changed lines) and copilot instructions for varlock.
varlock AGENTS.md
Instructions for dmno-dev/varlock, covering project conventions, repo structure, package manager, scripts and binary builds.
lingo.dev CLAUDE.md
Claude Code instructions for lingodotdev/lingo.dev, covering extremely important instructions for claude, fyi, tools, testing and changesets.
intlayer CLAUDE.md
Instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
flarestarter AGENTS.md
Instructions for FlareStarter/flarestarter, covering agents.md, what this is, structure, conventions and commands.
AnvilWiki AGENTS.md
Instructions for PNGTRID/AnvilWiki, covering agents.md, repository purpose, read these first, intended tech stack (verified, as of 2026-08-11) and architecture: code/config/content separation (critical).