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/tsedio/tsed-cli/agents-mdgit clone --depth 1 https://github.com/tsedio/tsed-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 | $0.00812 | $0.00812 |
| Opus 5 | $0.00406 | $0.00406 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
tsed-cli 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 today.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Yarn 4 + Lerna workspaces organize sources under packages/*: cli hosts command entrypoints and generator templates, cli-core handles DI/prompt infrastructure, cli-mcp exposes MCP servers and tools, while cli-plugin-* packages bundle framework-specific blueprints plus their own tests. cli-testing provides shared harnesses, templates live in packages/cli/templates, artifacts land in dist/, VuePress + TSDoc files stay in docs/, and tools/* holds automation scripts (TypeScript references, ESLint, Vitest installers).
Build, Test, and Development Commands
yarn build: runsmonorepo build --verboseacross every workspace.yarn build:references: refreshes TS project references after renaming or adding packages.yarn test: executes the Vitest suite once; add--coveragefor V8 reports.yarn lint/yarn lint:fix: applies the flat ESLint config + Prettier formatting used in CI.yarn docs:serve/yarn docs:build: runslerna run build && tsdocthen serves or builds the VuePress site.
Coding Style & Naming Conventions
Author TypeScript ES modules with 2-space indentation, double quotes, and trailing commas per the shared Prettier rules. Favor named exports and keep command providers in packages/cli/src/commands/**/NameCmd.ts, suffixing classes with Cmd. Tests and utilities mirror their source paths, ending in .spec.ts or .integration.spec.ts. Plugin packages follow cli-plugin-<feature> naming; templates underneath use kebab-case folder names. Keep import blocks sorted (enforced by eslint-plugin-simple-import-sort) and reserve default exports for entry aggregators such as packages/cli/src/index.ts.
Testing Guidelines
Vitest powers both unit and integration coverage. Co-locate fast tests next to implementation files, while scenario-heavy suites live under packages/*/test/**. Use yarn vitest packages/cli/src/commands/init/InitCmd.spec.ts to focus a file, prefer .integration.spec.ts when exercising generators end-to-end, and ship PRs with yarn test --coverage so CI can enforce thresholds. Mock filesystem access via helpers in cli-testing instead of touching the real disk.
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.
- today First seen · 32 lines · 812 tokens per session scan A 3a193c8581e0
tsed-cli AGENTS.md is an instructions file published in the GitHub repository tsedio/tsed-cli (43 stars, last pushed 13d ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 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 2026-09-01.
Other instructions, from other repositories
forem copilot-instructions.md
Copilot instructions for forem/forem, covering forem ai context & rules, meta: ai instruction synchronization, general philosophy, background workers & sidekiq and testing standards.
forem AGENTS.md
AGENTS.md instructions for forem/forem, covering forem ai context & rules, meta: ai instruction synchronization, general philosophy, background workers & sidekiq and testing standards.
forem CLAUDE.md
Claude Code instructions for forem/forem, a project described as: For empowering community 🌱.
webservice AGENTS.md
AGENTS.md instructions for trakli/webservice, covering agents.md, about trakli, rule: public content, rule: support trakli and rule: api responses use one envelope.
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.