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 somnus0x/agt-skill-pack --skill occamgit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote 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/somnus0x/agt-skill-pack/occam)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/occam"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/occam/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/somnus0x/agt-skill-pack/occam"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/occam.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 | $0.00043 | $0.01143 |
| Opus 5.5 | $0.00017 | $0.00457 |
| Sonnet 5.5 | $0.00009 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
occam 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Occam — The Simpler-Thing Test
You proposed a fix. Before it ships, prove the smaller version doesn't work.
Why
AI coding tools are biased toward comprehensive solutions. You ask for a bug fix, you get a new service with 10 columns, 3 methods, and wiring at 12 call sites. The bug needed one database constraint.
Occam forces a checkpoint: show the minimum version, the proposed version, and the overbuilt version side by side. Then justify why you're not shipping the smallest one.
This is NOT a veto. Some complexity is correct. The point is to make the trade explicit before you commit.
When to use
Explicit
Say /occam or "is this necessary", "feels complex", "simpler", "why is this so much code", "in my head it's just X".
Auto-fire (add to your CLAUDE.md)
Tell your AI to fire Occam automatically before finalizing any plan that introduces:
- A new database table or column whose only purpose is the current bug
- A new service, module, or provider
- A new helper class wrapping a single existing call
- A new background worker, cron, or scheduled job
- A new event type, queue, or pub/sub channel
- A new feature flag with only one consumer
- A function longer than ~60 lines that's mostly defensive branches
- Any abstraction justified by "we might need this later"
Don't fire for: one-line fixes, renames, test additions, config changes, following an existing pattern, or when you've explicitly said "go ahead, full version."
The four questions
Run in order. Show your work.
1. Restate the user-visible bug in one sentence
What does the user see today that they shouldn't? If you can't say it in one sentence, the fix scope is too broad.
Example: "When a user submits a form once, two identical records appear."
2. What is the minimum change that closes that exact sentence?
Often: one DB constraint, one early-return, one config flip, one bug fix in a single function. Resist the urge to refactor surrounding code.
Example: "Add a UNIQUE constraint. INSERT-or-skip on every request. ~30 LOC, no new module."
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.
- 1mo ago First seen · 126 lines · 43 tokens per session scan A 5788d959aa5f
occam is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,143 once invoked, about $0.0002 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…