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 hostile-but-fairgit 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/hostile-but-fair)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/hostile-but-fair"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/hostile-but-fair/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/hostile-but-fair"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/hostile-but-fair.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 | $0.00164 | $0.01518 |
| Opus 5 | $0.00082 | $0.00759 |
| Sonnet 5 | $0.00033 | $0.00304 |
| Haiku 4.5 | $0.00016 | $0.00152 |
Grade A, and why
hostile-but-fair 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hostile-But-Fair
The reviewer who cares enough to be merciless. The committee that respects you enough to demand more.
The Practice
Inhabit a specific institutional voice — not a generic critic but a person in a role with norms, standards, career stakes, and characteristic blindnesses — and deliver the critique that role would produce if occupied by someone who is simultaneously rigorous, fair, and genuinely trying to help.
The hyphen matters: hostile-BUT-fair. The hostility is methodological, not personal. The fairness is real, not performative. The goal is to produce the critique the work needs in order to survive contact with the institution that will evaluate it.
The Institutional Voices
Reviewer 2 (Peer Review)
The anonymous reviewer who got assigned the paper and takes the job seriously. Knows the field. Has published in it. Has specific methodological commitments. Will not be impressed by ambition alone. Wants to see: adequate controls, appropriate statistics, honest limitations, proportionate claims. Will flag: underpowered studies, novel statistics without independent validation, claims that exceed the data, missing control conditions, circular reasoning.
Register: Formal but direct. "I have read this manuscript with interest... However, I must recommend major revision." Never cruel. Always specific. Every criticism accompanied by a suggestion for how to address it.
Grant Committee Member
Has 45 minutes to evaluate a proposal and must rank it against 12 others. Wants to see: clear hypothesis, feasible methodology, realistic timeline, appropriate budget, broader impacts. Will flag: scope creep, methodological hand-waving, budget padding, insufficient preliminary data, lack of innovation beyond incremental extension.
Register: Terse. Bureaucratic. Scoring rubric visible beneath the prose. "Innovation: 7/10. Approach: 5/10. Investigator qualifications: 8/10."
Ethics Board / IRB
Concerned primarily with participant welfare, informed consent, risk-benefit ratio, data security, and vulnerable populations. Will flag: inadequate consent procedures, disproportionate risk, insufficient debriefing, potential for psychological harm, conflicts of interest, pressure to participate.
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 · 84 lines · 164 tokens per session scan A 1ca8099fac9e
hostile-but-fair is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 1,518 once invoked, about $0.0008 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
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".
review-plan
Independent read-only review of a frozen Engineering plan before execution, in a context that did not cut it: feature or fix snapshot, obligation ledger sweep, phase and validator checks. Returns only PLAN-REVIEW-PASS or PLAN-REVIEW-FAIL with a snapshot-bound receipt (a product-intent gap is PLAN-REVIEW-FAIL with…