Borrowing it
Nothing to install: this file belongs to jon-devlapaz/tink-skills. 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/jon-devlapaz/tink-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/jon-devlapaz/tink-skillsWrote 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/jon-devlapaz/tink-skills/agents-md)<a href="https://agentmods.dev/instructions/jon-devlapaz/tink-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jon-devlapaz/tink-skills/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/jon-devlapaz/tink-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jon-devlapaz/tink-skills/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 | $0.00508 | $0.00508 |
| Opus 5.5 | $0.00203 | $0.00203 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
tink-skills 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 15d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical skill tree: skills/
Read published skills from skills/. That directory is the source for this repository, including skill-gate. seed-me is the external skill at https://github.com/jon-devlapaz/seed-me.
Tink installs the locked set from .tink/skills.toml into .agents/skills/. .agents/ is installed state, not source, and is gitignored. Every local skills/<name> skill, including skill-gate, belongs in that install and must match skills/<name>. tink skill sync copies a missing install from the published tree. Sync refuses to overwrite an install whose body already differs; remove that .agents/skills/<name>/ directory and run tink skill sync again. Do not edit the installed copy.
Coding standards
- Read
CODING_STANDARDS.mdbefore writing or reviewing a skill or its tests.
Anti-patterns (observed, load-bearing)
- No silent skips. A defined step is attempted or its skip reason is recorded in the transcript. Discretionary wording that lets a host skip without a trace is a defect in the instruction, not flexibility.
git-golden
A repository is git-golden when all of the following are true:
- It is checked out on
mainwith a clean working tree. - Local
mainis even withorigin/main. - Open issues and pull requests are tracked separately; they do not make the checkout unclean.
- The latest
Validate repositoryrun onmainsucceeded.
SDLC Workspace
- Read
_system/SDLC.mdfor setup, evidence boundaries, and recovery. - Inspect
python3 _system/scripts/sdlc.py statusbefore creating a run. - Read
stages/<stage-name>/CONTEXT.mdbefore processing a stage. - Keep factory references in
_shared/unchanged during feature runs. - Use separate worktrees or clones for code-writing runs.
- Stage skills: see the Skills section of the current stage's CONTEXT.md.
- Need a specialised skill mid-task?
tink-route --receipt runs/<slug>/skills.jsonl "<what you need>"prints it on stdout; exit 1 means none fits, so continue without one.
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.
- 15d ago Changed · +17 tokens per session 2fc4e700f36f
- 19d ago Changed · +4 lines · +31 tokens per session f82cd6603852
- 22d ago Changed · +2 lines · +73 tokens per session 496b012326f9
- 28d ago Changed · +8 lines · +75 tokens per session ce16eb7bcf08
- 1mo ago Changed · +6 lines · +59 tokens per session f3382bf276ef
- 1mo ago Changed · +14 lines · +237 tokens per session ef8954a550ae
- 1mo ago Changed · -4 lines · -5 tokens per session 57bb5c56bec4
- 1mo ago First seen · 6 lines · 21 tokens per session scan A 5b4c46527a39
tink-skills AGENTS.md is an instructions file published in the GitHub repository jon-devlapaz/tink-skills (16 stars, last pushed 14d ago), licensed MIT. It adds 508 tokens to every session, about $0.0020 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.