Borrowing it
Nothing to install: this file belongs to guilhermehto/cogitator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/guilhermehto/cogitator/master/AGENTS.mdgit clone --depth 1 https://github.com/guilhermehto/cogitatorWrote 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/guilhermehto/cogitator/agents-md)<a href="https://agentmods.dev/instructions/guilhermehto/cogitator/agents-md"><img src="https://agentmods.dev/badge/instructions/guilhermehto/cogitator/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 5.1 | $0.00869 | $0.00869 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
cogitator 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
cogitator is a terminal (Bubble Tea) TUI that monitors locally running opencode instances discovered over mDNS, renders a live sessions view with attention signals, and (step-by-step, behind a workspace seam) launches/jumps/resumes git worktrees in tmux. Optional Taskwarrior pane. Go module github.com/guilhermehto/cogitator (Go 1.25), macOS + Linux only.
Layout
cmd/cogitator/— entrypoint + flags (--status,--demo,--debug,--bell).internal/ui/— Bubble Tea model/update/view (the only package that imports bubbletea).internal/state/,discovery/,supervisor/,oc/— mDNS discovery, SSE event ingest, opencode API (oc/generated.gois generated — see CONTRIBUTING).internal/workspace/,git/,harness/,tmuxctl/,pathnorm/— worktree launcher seam (config, roster, merge, git, harness registry, tmux control, canonical paths).internal/config/,logging/,taskwarrior/— config, logging, Taskwarrior client.docs/— VitePress site (self-contained npm package;npm run dev|buildinsidedocs/), deployed to GitHub Pages by.github/workflows/docs.yml.make democopiestui.pngintodocs/public/.
Commands
make ci— vet + lint + test + cross-build. Run before any PR.make test—go test -race -count=1 ./....make build/make run— build/run the binary.make generate— regenerate opencode API models (requires schema; see CONTRIBUTING).make demo— rebuildtui.pngfromdemo.tape(the--demoworktree roster) and sync it todocs/public/.
Demo / README screenshot
tui.png is generated from demo.tape with vhs. Run make demo (or a bare vhs demo.tape — the tape self-builds the gitignored binary first). Two non-obvious gotchas are baked into the tape/code; don't undo them:
- Font: use a well-tested patched Nerd Font (
Hack Nerd Font).vhsrenders through ttyd + headless Chrome, and0xProto's glyphs do not rasterize in xterm.js's WebGL atlas — they show as boxes even when the font is installed and contains the codepoints. - Colour:
RunDemoforceslipgloss.SetColorProfile(termenv.TrueColor). The vhs/ttyd pipeline isn't detected as a colour terminal, so without it the capture renders monochrome with no row-selection highlight band. - Deps (macOS):
brew install charmbracelet/tap/vhs ttyd && brew install --cask font-hack-nerd-font.
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.
- 8d ago First seen · 39 lines · 869 tokens per session scan A 8aa3bc85d1a3
cogitator AGENTS.md is an instructions file published in the GitHub repository guilhermehto/cogitator (2 stars, last pushed 19d ago), licensed MIT. It adds 869 tokens to every session, about $0.0043 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.