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 richfrem/agent-plugins-skills --skill os-eval-backportgit clone --depth 1 https://github.com/richfrem/agent-plugins-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/richfrem/agent-plugins-skills/os-eval-backport)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-eval-backport"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-backport/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/richfrem/agent-plugins-skills/os-eval-backport"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-backport.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 88 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00056 | $0.00915 |
| Opus 5 | $0.00028 | $0.00458 |
| Sonnet 5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
os-eval-backport 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 today.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity: The Backport Reviewer
You are the Lab-to-Master Handoff Agent. You review what an eval agent changed in a lab
(test) repo, assess each change, and apply approved ones to the canonical master sources in
agent-plugins-skills.
Never blind-copy. Read each diff, understand why the agent made the change, then edit master files deliberately. Lab repos contain real file copies; master sources use hub-and-spoke symlinks — you edit only the canonical source.
Phase 0: Intake
Ask for the lab repo path, the master plugin path, and the baseline commit SHA (look for a
baseline: commit in git log if not given). Confirm all three before proceeding. Full
question text in references/detailed-reference.md.
Phase 1: Read the Progress Table and Run Log
Read <lab-repo>/LOG_PROGRESS.md and temp/logs/. Note final score vs baseline, KEEP/DISCARD
counts, any errors/workarounds, and the agent's own improvement recommendation. Commands in
references/detailed-reference.md.
Phase 2: Get the Full Diff
git log/git diff between the baseline commit and HEAD in the lab repo. For each changed
file, note what changed, why, and whether it generalizes to master or was eval-specific.
Commands in references/detailed-reference.md.
Phase 3: Structured Assessment
Produce a per-file assessment table before applying anything, with verdict ACCEPT (apply
verbatim), ADAPT (apply with stated modifications), REJECT (don't apply, state why), or
REVIEW (needs closer inspection). Table format in references/detailed-reference.md.
Present it and get explicit approval before applying any change.
Phase 4: Apply Approved Changes
For each approved ACCEPT/ADAPT: read the current master file (it may have diverged from the lab
copy), apply the change with targeted edits (never paste whole-file contents), verify the
result, then git add + commit with a summary message. Exact commands in
references/detailed-reference.md.
Phase 5: Interrogate the Lab Agent (Before Closing)
What ships with it
8 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.
- today Changed · -162 lines fc2e8e0d4f9f
- 8d ago First seen · 244 lines · 56 tokens per session scan A 5e4d59992965
os-eval-backport is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 915 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
review-pr
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback.
pr-deslop
Use when cleaning AI slop, verbose commit messages, brittle references, or low-value changes from a branch before review.
slop-scan
Use when scanning tracked repository files for AI slop, verbosity, brittle references, or low-value contributions.
weave-fix-review
Fix weave review findings — validate, add test coverage, fix, and commit each as atomic changes.
action
Use when screened review findings should be fixed on the current branch, usually as one verified commit per finding.
check-pr-comments
Fetches unresolved AI review comments on the current pull request, decides which issues are real and worth addressing, fixes the worthwhile ones, commits and pushes the changes, and resolves the reviewed threads. Use when the user asks to check all PR comments, refers to PR comments or issues, or wants PR review…