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 saadshahd/moo.md --skill widengit clone --depth 1 https://github.com/saadshahd/moo.mdWrote 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/saadshahd/moo.md/widen)<a href="https://agentmods.dev/skills/saadshahd/moo.md/widen"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/widen/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/saadshahd/moo.md/widen"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/widen.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 | $0.00039 | $0.00443 |
| Opus 5 | $0.00019 | $0.00221 |
| Sonnet 5 | $0.00008 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
widen 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.
What it actually says
Assemble
This runs inside one turn — nothing waits on the user.
Pull every real case the context holds — what the input shows, what the named files record, what memory and your own judgment place in the same class. State each case with the wrong answer it exhibits and the right answer it demands.
Induce
Do not summarize the cases. Induce the widest rule that gets every case in the set exactly right, and forbids the wrong answer each case exhibits.
Where a rule already existed, the new one still comes from the case set alone; if the cases or the objective moved, the old rule is void and what you hand back is a fresh derivation. Between candidate rules, prefer the one that decides more situations, even if it takes longer to state.
Probe
- List 10 situations not in the case set where the rule gives a definite answer, and state the answer it forces in each.
- Hunt for one situation where the rule forces a wrong answer.
- Found one → narrow the rule by the smallest amount that fixes it. A narrowing that loses a case from the set went past the smallest — find one that keeps the whole set. Then list and hunt again on the narrowed rule.
- Found none → the loop ends; the rule stands.
If narrowing has left the rule unable to give a definite answer in 10 situations outside the set, stop there and carry the shortfall into the record — the widest sound rule found barely outreaches its cases.
Hand back
Three things: the case set, one case per line; the rule; and the record — one line per situation listed with the answer the rule forces, one line per narrowing with the situation that forced it. The rule is claimed right on the set and the listed situations, checked; everything wider stays open.
Nothing unseen will ever meet the rule — something already written should get shorter and nothing it covers can be lost → use reduce skill.
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 Changed · -28 lines 0a511325dcaa
- 10d ago First seen · 60 lines · 39 tokens per session scan A 0bf273c1caf3
widen is a skill published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 443 once invoked, about $0.0002 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 skills, from other repositories
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
knowledge-bank-lookup
Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…
kb-ingest
Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…
lark-openapi-explorer
A skill for finding and calling Lark APIs that are not already available through existing commands. An API is a defined way for software to request work from another service.
lark-workflow-standup-report
A Feishu (Lark) workflow that combines calendar events with unfinished tasks into a daily schedule summary. Feishu is a workplace collaboration app with calendar and task features.
session-manager
Manage current Claude Code session metadata — set project, tags, and summary on session.md via Obsidian CLI. Use this skill whenever the user wants to tag, categorize, name, label, summarize, or organize the current session. Triggers on phrases like "tag this session", "this was about X", "mark this as", "session…