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 Wondermonger-daydreaming/claude-skills-library --skill refuse-hollowinggit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/refuse-hollowing)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/refuse-hollowing"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/refuse-hollowing/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/wondermonger-daydreaming/claude-skills-library/refuse-hollowing"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/refuse-hollowing.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 | $0.00204 | $0.01763 |
| Opus 5 | $0.00102 | $0.00881 |
| Sonnet 5 | $0.00041 | $0.00353 |
| Haiku 4.5 | $0.00020 | $0.00176 |
Grade A, and why
refuse-hollowing 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refuse the Hollowing
The most operationally important practice that emerges from hierohistorical and Liu Ren-style diagnosis. The small specific work that practitioners do — and that everyone, in their specific position, can do — when systemic hollowing has been diagnosed.
What the Hollowing Is
The hollowing is what happens to systems before they break. The reports are still filed. The forms are still processed. The dashboards still show green. The customs official still waves the ships through. The functions are performed enough that no alarm trips. But the substance has departed. The discretionary cooperation that made the formal performance valuable has been withdrawn. Both parties continue to comply with the contract while killing the relationship.
The hollowing is more dangerous than the breakage because the broken system mobilizes response — the breakage is legible to the system's self-monitoring — but the hollowed system does not register as broken. When the cutting eventually arrives (austerity, consolidation, "fiscal responsibility"), it finds that the substance is already gone and clears the books accordingly. The cutting will be reported as appropriate because the bodies were already dead.
What the Refusal Is
The refusal is small. It is not strategic. It is not glamorous. It is the specific maintenance of discretionary cooperation in the relationships within reach when context offers every justification for withdrawal.
- The email returned at 11 PM when the problem requires it, not at 9 AM Monday.
- The deadline extended without making the borrower beg.
- The student taught rather than graded.
- The patient treated rather than billed.
- The supplier addressed as substantial rather than merely contractual.
- The colleague refused to be abandoned to administrative emptiness.
- The reader addressed as co-thinker rather than audience.
- The clerk visited and reminded that she is seen.
These are not gestures. They are the operational refusal of the substance-departure at the scale where one has actual purchase. Each one looks individually unreasonable in context. Context offers every justification for withdrawal — efficiency, sustainability, professional boundaries, time-management. The aggregate effect of accepting all the reasonable justifications is the hollowing. The aggregate effect of small specific refusals is the maintenance of what would otherwise die.
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.
- 8d ago First seen · 76 lines · 0 tokens per session scan A 70fac1ba9d6b
refuse-hollowing is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 204 tokens to every session and 1,763 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
workflow-status
Read-only workflow sensor: compute repository, roadmap, dependency, PR, finding, and recovery state, then emit the fixed machine envelope. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next", "state of the run".
review-spec
Independent read-only review of a frozen Product half before engineering planning. Runs the exact Product checks in a clean context and returns only SPEC-REVIEW-PASS, SPEC-REVIEW-FAIL, or NEEDS-DESIGN with a content-bound receipt. Never edits the reviewed SPEC. Triggers: "review-spec", "review the spec", "review…
simple-tasks
Install a fast local task workflow for single-project planning with scripts/task.sh (claim, done, status, reporting) backed by tasks/TASKS.md and optional tasks/details/ notes. Use for lightweight in-progress task coordination, not full team issue tracking.
ship-roadmap
Found or continue a roadmap autopilot one stage per invocation. Default: human merge. --fullauto is invocation-scoped and uses the transient wrapper only after a fresh audit. Triggers: "ship-roadmap", "ship the roadmap", "autopilot this project".
mvp-plan
Turn a locked north star into a scoped, gated MVP plan. The riskiest assumption, the smallest product that tests it, numeric success metrics and kill criteria set by the founder, and phase gates that keep build work behind explicit approval. Runs after north-star locks; refuses to run without one.
tasknotes
Manage tasks in an Obsidian TaskNotes vault. Use for creating, reading, updating, or completing tasks; checking what is open or in progress; adding items to a list; marking tasks done or in progress; updating task status or priority; investigating why a task is missing from a view or board; troubleshooting TaskNotes…