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-acceptancegit 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-acceptance)<a href="https://agentmods.dev/skills/derio-net/super-fr/fr-acceptance"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-acceptance.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.00816 |
| Opus 5 | $0.00041 | $0.00408 |
| Sonnet 5 | $0.00016 | $0.00163 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
fr-acceptance 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fr-acceptance
The matrix (docs/acceptance/matrix.yaml) is the registry of business-level
acceptance tests × verification levels (unit/api/int/ui) × automation status.
This skill drives the agent-side work; the mechanics live in the CLI.
Announce at start: "I'm using fr-acceptance to work the acceptance matrix."
Statuses — the honesty scale
ci / scheduled = automated, cannot drift · skipped = verification exists
but not in CI (warning, backfill owed) · not-implemented = nothing yet
(warning) · failing = known red, fr acceptance check exits 2 and CI fails.
Statuses move explicitly, never silently. The drift channel is precisely
the hand-tracked claims — when in doubt between ci and skipped, choose skipped.
Do not inflate coverage; the operator audits statuses at review.
Backfill an existing repo
fr acceptance init(idempotent) if the repo has no matrix — scaffolds matrix + CI workflow + backfill rule + gitignore entry.fr acceptance backfill— emits the inventory (Test Plan specs not yet cited, plans without linked rows, test-tree hints) + this protocol.- DRAFT rows — one row per business acceptance, not per test — via
fr acceptance add --id <kebab> --capability <group> --acceptance "<operator can X>" --origin <repo>:<path> --level unit=<repo>:<path> --status <honest> --notes "<evidence / backfill owed>". Never hand-edit YAML shapes;addvalidates and appends. fr acceptance check→ fix errors (unresolved refs, staleness, schema), re-run until only honest warnings remain.- Open a review PR: the operator audits every status.
Flip statuses (execution hand-off)
When a plan phase carrying acceptance: [row-ids] completes, flip those rows
up the ladder (not-implemented → skipped → ci/scheduled), citing the
test refs that justify the move in levels and notes. fr plan edit --complete-phase warns on unflipped rows — fix or record why in the
completion note.
Mid-flight additions (encouraged, then defended)
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.
- 7d ago First seen · 67 lines · 81 tokens per session scan A b97623811771
fr-acceptance is a skill published in the GitHub repository derio-net/super-fr (1 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 816 once invoked, about $0.0004 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
phx-work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.