Borrowing it
Nothing to install: this file belongs to kimgh06/Thask. 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/kimgh06/Thask/main/AGENTS.mdgit clone --depth 1 https://github.com/kimgh06/ThaskWrote 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/kimgh06/thask/agents-md)<a href="https://agentmods.dev/instructions/kimgh06/thask/agents-md"><img src="https://agentmods.dev/badge/instructions/kimgh06/thask/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kimgh06/thask/agents-md"><img src="https://agentmods.dev/badge/instructions/kimgh06/thask/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00669 | $0.00669 |
| Opus 5.5 | $0.00268 | $0.00268 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
Thask 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thask — Project Instructions for AI Agents
Canonical agent guide: Thask.md (MCP thask.guide / CLI thask guide).
This file holds project-level conventions that the canonical guide does not cover.
Release tracking convention
When a new version of Thask is published to npm / GitHub, record it in the prod
Thask graph (project a9116af4-d6d1-416f-8c40-de31be0f5f49) using this pattern:
- Create a
TASKnode titledRelease vX.Y.Z, statusPASS, tagrelease. Description = the matchingCHANGELOG.mdsection (full markdown, including npm + GitHub Release links at top). - For every existing node this release ships (e.g. a feature TASK that was
IN_PROGRESS), update its status toPASS. - Add a
relatededge from the release node to each shipped node withlabel: "ships". - Call
thask.graph.layout(dagre)once at the end.
Why: thask.impact.analyze --node <release-id> then answers "what areas did this release touch" without re-reading commits. CHANGELOG.md stays the human-facing source of truth; the graph adds the structural view for agents.
Build / test / release
- Backend:
cd backend && go build ./... && go test ./... - Frontend:
cd frontend && npx svelte-check - CLI:
cd cli && go build ./... && go test ./... - Release pipeline (needs npm OTP):
make release-cli CLI_VERSION=X.Y.Z THASKOTP=<6-digit>
Release rules
- Docs must be fully up to date before
make release-cliruns. Treat it as a gate, not a follow-up. Pre-release sweep covers: CHANGELOG, README, ARCHITECTURE, API.md, CLI.md, MCP.md, DATABASE.md, CLAUDE_CODE_PLUGIN.md, GRAPH.md. CHANGELOG alone is necessary but not sufficient — README and ARCHITECTURE are the easy-to-forget ones. - If you're blocked on an external dependency mid-release (npm token, OTP, gh auth), use the wait window to do the doc sweep rather than skipping it.
Commit rules
- Never commit without an explicit per-task user request. Prior authorization does not carry over.
- Split commits by functional unit (refactor / feat / fix / docs separately), not bundled.
- Run code review before committing when the user asks for a commit.
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.
- 1mo ago First seen · 48 lines · 669 tokens per session scan A 766abbf5ebd0
Thask AGENTS.md is an instructions file published in the GitHub repository kimgh06/Thask (8 stars, last pushed 3mo ago), licensed MIT. It adds 669 tokens to every session, about $0.0027 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.