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 ur-grue/autopunk-media-skills --skill ethics-review-checklistgit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/ethics-review-checklist)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/ethics-review-checklist"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/ethics-review-checklist/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/ur-grue/autopunk-media-skills/ethics-review-checklist"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/ethics-review-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.10010 |
| Opus 5 | $0.00023 | $0.05005 |
| Sonnet 5 | $0.00009 | $0.02002 |
| Haiku 4.5 | $0.00005 | $0.01001 |
Grade A, and why
ethics-review-checklist 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ethics Review Checklist
What This Skill Does
Generates a publication-specific editorial ethics checklist tailored to the risks of a particular story — covering consent, harm minimization, source protection, vulnerable subjects, conflicts of interest, right of reply, public interest justification, and legal exposure.
When To Use This Skill
- A story is approaching publication and the editor wants a documented record that all ethical obligations have been considered before sign-off
- The story involves named individuals who did not initiate contact with the publication — they were found, identified, or exposed by the reporting
- The story names or could identify vulnerable subjects: minors, crime victims, people experiencing mental health crises, refugees, or anyone in a position where publication could cause direct harm
- A source has been promised anonymity and you need to verify that the published text does not inadvertently identify them through detail accumulation
- The reporter has a potential conflict of interest — personal relationship with the subject, financial interest in the outcome, prior public statements on the issue
- The story could cause reputational, financial, or physical harm to named individuals and you need to document the public interest justification for publication
- You are editing an investigative piece and want to ensure right of reply has been offered to everyone who is accused or characterized negatively
- A legal threat has been received and you need to document the ethical basis for proceeding with publication
What You Need To Provide
Required: A summary of the story (500+ words preferred), including: the central claim or narrative, who is named or identifiable, what allegations or characterizations are made about them, how sources were obtained, and whether any sources requested anonymity.
Optional: The publication's code of ethics or editorial standards (if one exists); the jurisdiction of publication (ethics standards vary by country and press council); whether legal counsel has already reviewed the draft; the publication timeline and any external pressure to publish (competitive, legal deadline, news cycle); prior correspondence with subjects (especially any right-of-reply responses or legal threats); the reporter's relationship to the story or subjects.
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 · 561 lines · 46 tokens per session scan A 888380bf6853
ethics-review-checklist is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 46 tokens to every session and 10,010 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 2026-09-04.
Other skills, from other repositories
foia-requests
FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.
content-access
Legal methods for paywalled and geo-blocked content. Use for paywalls, academic papers, or open access via Unpaywall.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
brazil-records-requests
Public records requests under Brazil's Access to Information Law (LAI). Use for Fala.BR filings, e-SIC, and CGU/CMRI appeals.
interview-prep
Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.
web-archiving
Archive evidence before it disappears — first-party snapshot (MHTML + screenshot, content-addressed) by default, plus third-party archives, with chain of custody for editorial accountability and legal defensibility.