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 derio-net/super-fr --skill fr-originsgit clone --depth 1 https://github.com/derio-net/super-frWrote 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/derio-net/super-fr/fr-origins)<a href="https://agentmods.dev/skills/derio-net/super-fr/fr-origins"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-origins/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/derio-net/super-fr/fr-origins"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-origins.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 | $0.00061 | $0.01590 |
| Opus 5.5 | $0.00024 | $0.00636 |
| Sonnet 5.5 | $0.00012 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
fr-origins 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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fr-origins
Announce at start: "I'm using fr-origins to classify the issues filed in since ."
You can already read an issue and the code it names. A classification done in chat dies with the session; fr triage origins keeps it in a file, so a re-run costs only the issues that arrived.
State: two files, two owners
Everything lives in the scope's triage state directory, the same one fr triage uses (the workspace's .fr/triage-state/<scope>/, or ~/.cache/fr/triage/<scope>/ outside a clone; --dir D overrides). Pass the same scope options to every command: --repo OWNER/REPO, a comma-separated group --repo A/B,C/D, or --org OWNER.
| File | Written by | Holds |
|---|---|---|
origins-facts.json |
fr triage origins collect --since DATE |
the issues created since the date: labels, state and reason, closing PRs, hours to close |
origins.yaml |
you | one classification per issue, plus the causes: the conclusion links to batches |
origins.html |
fr triage origins render |
the page, built from both (and judgements.yaml, only to resolve batch ids) |
Never write the facts yourself. The state is outside every repo and is never committed.
The loop (a re-run of it is the sync)
- Collect.
fr triage origins collect --repo OWNER/REPO --since YYYY-MM-DD. A window wider than one page of issues or PRs is refused (exit 2), naming a--sinceit does cover and the limit flag (--issue-limit,--pr-limit) to raise instead: narrow the window and report the narrower one, or raise the limit to keep it. A warning that the repo list hit its limit means repos may be missing; say so in your report. - Check.
fr triage origins check --repo OWNER/REPOlists unclassified issues (your work queue), classifications for issues not in the facts (a typo, or a window that moved; never pruned for you; fix the key or leave it), and duplicate target outside the window (aduplicate_ofnaming an issue the facts do not hold: widen--since, or confirm the key). It always exits 0. - Classify the unclassified, from the issue body and the code, as below.
- Render.
fr triage origins render --repo OWNER/REPOwritesorigins.html. A figure the data cannot support shows as an em dash, never a zero; do not paper over one. - Conclude. Fill
causes:and link each to the batch that addresses it (fr triage batch listnames them; a batch id that does not exist is shown as unresolved, so fix it rather than leave it).
What ships with it
1 file 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.
- 6d ago Changed 18a07e28eaf8
- 9d ago Changed · +5 lines 5a2c61638384
- 12d ago First seen · 72 lines · 61 tokens per session scan A 030ca334e322
fr-origins is a skill published in the GitHub repository derio-net/super-fr (2 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 1,590 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
bug-fixer
A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.
simplify
Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior.