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 skills add dirtybits/agent-skills --skill skills-organizationgit clone --depth 1 https://github.com/dirtybits/agent-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/skills/dirtybits/agent-skills/skills-organization)<a href="https://agentmods.dev/skills/dirtybits/agent-skills/skills-organization"><img src="https://agentmods.dev/badge/skills/dirtybits/agent-skills/skills-organization/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/skills/dirtybits/agent-skills/skills-organization"><img src="https://agentmods.dev/badge/skills/dirtybits/agent-skills/skills-organization.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 | $0.00092 | $0.02328 |
| Opus 5 | $0.00046 | $0.01164 |
| Sonnet 5 | $0.00018 | $0.00466 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade B, and why
skills-organization scanned grade B with 1 finding 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 9d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Do not use `rm -rf` for reconciliation. Move to backups instead. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Organization
Use this skill when keeping local agent skill folders aligned across tools. Treat it as a power-user local workflow: audit first, explain the isolation tradeoffs, then make writes only after the user approves the exact paths.
Core Stance
- Treat
~/.agents/skillsas the canonical source of truth for personal/shared skills. - Mirror an agent tool's normal
skillspath to the canonical root with a directory symlink only when the user intentionally wants shared cross-agent skills. - Prefer a hub-and-spoke layout over cross-linking every directory to every other directory.
- Do not blindly import product-managed, vendor-managed, plugin-cache, backup, or bundled skill directories.
- Shared storage does not guarantee shared compatibility. Codex, Claude, Cursor, Hermes, OpenClaw, and other tools may expect different skill schemas, frontmatter, file layouts, or install metadata.
- Preserve anything you replace. Move real directories to timestamped backups before creating symlinks.
Hermes Profile Warning
Hermes can use both the active-profile skills path and named profile skill directories:
- Active profile:
~/.hermes/skills - Named profiles:
~/.hermes/profiles/<profile>/skills
Only link ~/.hermes/skills if the user explicitly wants the active Hermes profile to share the common skill set. Do not symlink ~/.hermes/profiles/*/skills automatically. Profile directories can represent intentionally isolated contexts, and flattening them into ~/.agents/skills can make skills from one context bleed into another.
If the user wants Hermes integration but not shared storage, prefer normal Hermes skill install or management commands and leave profile-specific directories alone.
Why Not Cross-Link Everything?
If ~/.codex/skills, ~/.claude/skills, and ~/.cursor/skills are symlinks to ~/.agents/skills, then adding a skill through any of those paths already lands in the shared directory. A mesh of symlinks between tool directories is harder to reason about, easier to loop, and offers no practical benefit over one canonical target.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 189 lines · 92 tokens per session scan B 89ee939a65e0
skills-organization is a skill published in the GitHub repository dirtybits/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,328 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
workflows
A workflow guide for tasks that need several kinds of reasoning in sequence, such as research, finding the main conflict, choosing a small starting point, and planning sustained work.