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/vanillagreencom/kendex/agents-mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWhat 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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
kendex 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kendex
Desktop app + thin CLI (Rust + Tauri + React) for managing AI coding-harness customizations.
Orientation. Read docs/ARCHITECTURE.md before structural work; stale docs are bugs — amend them in the same change. Open work lives in Linear (team KEN); scratch goes to tmp/ (gitignored), never /tmp. Review bots follow review-bots.md and .github/instructions/*.instructions.md. Engineering rules are the code-quality skill; round scope is the dev skill's § Engineering Rules; finding dispositions are orch's references/finding-disposition.md.
Repo-specific rules:
crates/coreis pure domain logic — no Tauri, no IPC, no UI concerns.ui/renders state and invokes commands; domain logic and types live in Rust, and TS bindings are generated, never hand-written.- The CHANGELOG is for consumers (Keep a Changelog): document app, CLI, and package changes; keep engine-internal and maintainer-only details out. An entry runs at most 200 characters — the outcome, a Breaking: migration inline,
— thanks @namefor outside contributors — never an essay. - An entry is a file, never a
CHANGELOG.mdline: writechangelog.d/<section>/<name>.mdholding the list item it becomes, perchangelog.d/README.md..agents/skills/growth-guards/scripts/changelog-entries --collatefolds them in at release. - Where a skill has a rendered copy under
.agents/skills/, a change to the source lands that copy in the same commit; the same holds foragents/<n>.mdand its per-harness renders, and for ahooks/<n>change, which lands whichever harness hook copies already track it — judged per file, because the harness hook sets are deliberately not uniform andhooks/tests/*renders nowhere.tools/guardreds any such source change whose render does not move with it — presence, not byte equality, because where the project declares skill instructions for a skill, its render carries an injected block the source has no copy of, marked in the file by the renderer. A source with no tracked render has nothing to land. ui/installs withnpm ci --prefix ui, in the main checkout only.- Every suite and the aggregator over them run on the pull request as well as in the merge queue, so a green PR proves what the queue re-proves and a red shard blocks the PR itself — fix it there rather than requeuing. Anything in
.github/workflows/skill-tests.ymlthat does not run on every event carries anif:saying why.
tools/guard enforces the rest — read the script; it is the list. It is the last lane of the package's commit chain, named by GROWTH_GUARDS_PRE_COMMIT_LOCAL; tools/setup arms that chain in a fresh clone, beside the package's own commit-msg gate. Neither judges a hook below its delegating line: a .git/hooks/commit-msg calling a repo-local tools/commit-msg lane — which this repo does not have — blocks every commit until you delete that hook and run setup again. That gate holds the three rules only a commit message can carry: the header is type(scope)!: subject, the whole header line caps at 72 characters, and a change under crates/ or ui/ ships a changelog fragment or says [no-changelog] in the subject.
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 Changed · +5 lines · +232 tokens per session 44b67ebe9957
- 2d ago First seen · 36 lines · 818 tokens per session scan A 1ddf6bcda342
kendex AGENTS.md is an instructions file published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed today), licensed MIT. It adds 1,050 tokens to every session, about $0.0052 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
pi-agent-browser-native AGENTS.md
Instructions for fitchmultz/pi-agent-browser-native, covering pi-agent-browser-native, product-specific guidance, documentation placement, upstream capability baseline and command reference and tool result categories.
supi CLAUDE.md
Instructions for mrclrchtr/supi, covering claude.md, development status, pi docs-first rule, documentation expectations and package layout convention.
pi-extensions AGENTS.md
Instructions for MattDevy/pi-extensions, covering pi-extensions, repository structure, commands (run from repo root), working on a specific package and readme conventions.
pi-extensions CLAUDE.md
Instructions for MattDevy/pi-extensions, covering claude.md, commands, architecture, data flow and key modules.
pi-codex-goal AGENTS.md
Instructions for fitchmultz/pi-codex-goal, covering pi-codex-goal — agent notes, local pi install policy, verify before finishing and layout.
pi-commandcode-provider AGENTS.md
Instructions for patlux/pi-commandcode-provider, a project described as: pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen.