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/sananthanarayan/skilldrop/agents-mdgit clone --depth 1 https://github.com/sananthanarayan/skilldropWhat 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 | $0.07594 | $0.07594 |
| Opus 5 | $0.03797 | $0.03797 |
| Sonnet 5 | $0.01519 | $0.01519 |
| Haiku 4.5 | $0.00759 | $0.00759 |
Grade A, and why
skilldrop 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 2d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidance for Autonomous Coding Agents
Canonical guide for Copilot, Codex, Cursor, and other agentic IDEs operating on this repository.
Repo in one paragraph
skilldrop is a collection of portable Claude Skills for the deliverables knowledge workers actually ship: diagrams, ADRs, design docs, runbooks, decks, decision logs, comparison matrices, exec summaries, structured critiques, and adversarial code review. Each skill is a plain directory under skills/ containing a SKILL.md + manifest.json (+ optional reference.md, templates/, lenses/, rubrics/, examples/, scripts/, requirements.txt). Installation is per-folder copy into the target IDE's skills/rules location — documented per-IDE install steps live in README.md (Claude Code, Cursor, Kiro, Continue, Cline, Aider).
Golden rules
- Folder name =
SKILL.mdname=manifest.jsonname. Kebab-case, use-case-first, no version suffix. Changing any of the three without the others breaks slash-command invocation. - Do not move
skills/,LICENSE, orREADME.md. Skills are discovered by path; moving the directory breaks every install instruction the README documents. - Keep
SKILL.mdunder ~500 lines. Spill intoreference.md,templates/,lenses/,rubrics/, orexamples/. Agent context is the binding constraint — a bloatedSKILL.mdcrowds out the user's actual prompt. - Never invent commands, env vars, or file conventions. Use those documented below. The only automated checks are
python3 validate.pyandnode bin/skilldrop.js validate, run locally and by CI (.github/workflows/release.yml, which also publishes to npm on version bump — see Releasing). Don't pretend other test runners or linters exist. - No secrets, no real customer names, no personal data in templates, examples, or sample inputs. Placeholder data only.
- Voice is opinionated, not hedged. Strip "generally", "consider", "you might want to". The
✅/❌markers have semantic meaning — don't use them decoratively, don't add other decorative emoji. - Every new skill ships with
Quality barandAnti-patterns to avoidsections. A skill without them is a description, not a generator. Both are enforced byvalidate.py(RFC-0016).
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.
- 2d ago First seen · 313 lines · 7,594 tokens per session scan A 501a8f7487b4
skilldrop AGENTS.md is an instructions file published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed 18d ago), licensed MIT. It adds 7,594 tokens to every session, about $0.0380 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
mcp-adr-analysis-server copilot-instructions.md
Instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.
nullius CLAUDE.md
Instructions for armanfatemi/nullius, covering nullius, commands, known-environmental test failures, evidence anchors — the house rule and dogfooding gates (ci runs all of these).
adrkit copilot-instructions.md
Instructions for mbeacom/adrkit, covering adrkit — github copilot and github copilot specifics.
docflow AGENTS.md
Instructions for EvolveHQ/docflow, covering agents.md, what this repository is, repository structure, hard rules when editing adrs and domain-specific hard rules.
adr-kit AGENTS.md
Instructions for rvdbreemen/adr-kit, covering adr-kit agent instructions, task management, repo conventions, verification and adr kit.
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.