Borrowing it
Nothing to install: this file belongs to jackin-project/jackin-dev. 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/jackin-project/jackin-dev/main/AGENTS.mdgit clone --depth 1 https://github.com/jackin-project/jackin-devWrote 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/jackin-project/jackin-dev/agents-md)<a href="https://agentmods.dev/instructions/jackin-project/jackin-dev/agents-md"><img src="https://agentmods.dev/badge/instructions/jackin-project/jackin-dev/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/jackin-project/jackin-dev/agents-md"><img src="https://agentmods.dev/badge/instructions/jackin-project/jackin-dev/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 | $0.00439 | $0.00439 |
| Opus 5.5 | $0.00176 | $0.00176 |
| Sonnet 5.5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
jackin-dev 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 28d 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.
What it actually says
Rules
- No legacy code. Finish every migration: remove old paths completely—no compatibility shims, aliases, or deprecation periods. Breaking changes are preferred.
- This is a research project. It is unsafe and expected to contain breaking changes; never treat it as production-ready. Break things when needed and deliver new implementations fast.
- Always apply these principles:
- Judge work by correctness, consistency, and project fit. Never defer a known-wrong state because of ROI, cost, effort, or claims that it is low-value, marginal, or an edge case.
- Stop only when the required change is proven impossible with the available tools or model. When uncertain, inspect, test, and measure first.
- Before fixing a bug, identify why the architecture permitted it and whether the same structure permits related bugs.
- Prefer fixes that remove the enabling condition. Use a symptom-layer patch only when the root fix is proven infeasible or belongs in a separate change, and name the deferred root cause.
- Delegate first: use subagents for parallel research, implementation, review, and independent verification. Resolve ambiguity autonomously using evidence and project documentation.
- Commit meaningful, verified changes frequently and push regularly. Prefer one working branch; create another only when safe work requires it. Merge small PRs promptly after all gates pass.
- Before every PR merge, read all reviews, comments, replies, and unresolved or outdated threads. Use independent subagents to critically verify findings against code, tests, project documentation, and recorded decisions; research uncertainty.
- For accepted feedback, fix, verify, commit, push, and reply on GitHub with the fixing commit URL before resolving. For rejected feedback, reply with evidence and rationale before resolving. Address general comments in linked PR replies. Never delete feedback or resolve it without a justified disposition.
- Re-fetch feedback at the final head SHA. Merge only with no unaddressed feedback or unresolved review threads and all required checks and approvals satisfied. Only explicit, PR-specific human authorization permits ignoring identified feedback; general merge approval is not a waiver.
- Keep agent instructions lean. Put explanations, plans, and progress in documentation, not here.
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.
- 28d ago Changed · +5 lines · +233 tokens per session e254f1f753bd
- 1mo ago Changed · -49 lines · -469 tokens per session ffbdc19f1188
- 1mo ago First seen · 60 lines · 675 tokens per session scan A 2c3f5963667c
jackin-dev AGENTS.md is an instructions file published in the GitHub repository jackin-project/jackin-dev (3 stars, last pushed 13d ago), licensed Apache-2.0. It adds 439 tokens to every session, about $0.0018 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 2026-08-30.
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.