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/massimodeluisa/recursive-decomposition-skill/agents-mdgit clone --depth 1 https://github.com/massimodeluisa/recursive-decomposition-skillWrote 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/massimodeluisa/recursive-decomposition-skill/agents-md)<a href="https://agentmods.dev/instructions/massimodeluisa/recursive-decomposition-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/massimodeluisa/recursive-decomposition-skill/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 | $0.00321 | $0.00321 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
recursive-decomposition-skill 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 6d 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
Agents: recursive-decomposition skill
Entrypoint for agentic tooling working on this repository.
Read these first (mandatory)
| Doc | Why |
|---|---|
| CONVENTIONS.md | Skill format, sources, prose, git, versioning, validation |
| CONTRIBUTING.md | Change workflow |
| skills/recursive-decomposition/SKILL.md | The skill itself |
| CHANGELOG.md | Release history |
Follow CONVENTIONS.md for every change. This file is a short checklist only. CLAUDE.md is a symlink to this file.
Language policy
- Markdown, manifests, commits: English only.
Non-negotiables
- Every number or claim about the paper cites arXiv:2512.24601; nothing invented.
SKILL.mdstays under 500 lines with a single-line, double-quoted description.- The skill name and the plugin name never change.
- Bump
versionin.claude-plugin/plugin.jsonandSKILL.mdtogether on every user-visible change. - No em dash, no filler, no co-author trailers, no Python.
Commands
bash .github/scripts/validate-skill.sh
npx -y skills@latest add . -l
claude plugin validate .
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.
- 6d ago First seen · 35 lines · 321 tokens per session scan A 4b5ae726458e
recursive-decomposition-skill AGENTS.md is an instructions file published in the GitHub repository massimodeluisa/recursive-decomposition-skill (46 stars, last pushed 8d ago), licensed MIT. It adds 321 tokens to every session, about $0.0016 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 2026-08-30.
Other instructions, from other repositories
csift CLAUDE.md
Claude Code instructions for wdhwg001/csift, a project described as: The missing tool to sift your Claude Code sessions: regex search across all record types, recover files, extract images, inspect subagent topologies, match between plan files and sessions.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
qector-claude-plugin AGENTS.md
AGENTS.md instructions for GuillaumeLessard/qector-claude-plugin, covering policylayer playbook, repository guidelines, project structure & module organization, build, test, and development commands and coding style & naming conventions.
chealth CLAUDE.md
Instructions for danielithomas/chealth, covering claude.md, project purpose, language & tooling, build & test and architecture.
odoo-superpowers CLAUDE.md
Claude Code instructions for omas-odoo/odoo-superpowers, covering odoo superpowers — values & conventions, who this is for, hard rules (machine-enforced), core values and skills.
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).