Borrowing it
Nothing to install: this file belongs to bonginkan/fairy_tale. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bonginkan/fairy_tale/main/.agents/skills/fairy-tale-legal-feedback/SKILL.mdgit clone --depth 1 https://github.com/bonginkan/fairy_taleWrote 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/bonginkan/fairy_tale/fairy-tale-legal-feedback)<a href="https://agentmods.dev/skills/bonginkan/fairy_tale/fairy-tale-legal-feedback"><img src="https://agentmods.dev/badge/skills/bonginkan/fairy_tale/fairy-tale-legal-feedback/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/bonginkan/fairy_tale/fairy-tale-legal-feedback"><img src="https://agentmods.dev/badge/skills/bonginkan/fairy_tale/fairy-tale-legal-feedback.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 | $0.00892 |
| Opus 5.5 | $0.00018 | $0.00357 |
| Sonnet 5.5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
fairy-tale-legal-feedback 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 2mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fairy Tale Legal Feedback
Use this skill after a legal benchmark miss, on high-risk legal work product, or when a legal task resembles known weak areas from the 2026-06-14 LAB-style sample.
Do not read grading rubrics or hidden expected answers. Use only task instructions, provided matter documents, authorized tools, and the visible work product.
Failure Classes
near_miss_final_criterion: one missing requirement, caveat, citation, clause, date, party, threshold, schedule, exhibit, or signature item.small_coverage_gap: two or three missed requirements.moderate_coverage_gap: several missed requirements despite a plausible top-level structure.domain_scaffold_gap: a practice area needs a domain-specific checklist.large_draft_collapse: a long draft lost clause architecture, defined terms, cross-references, schedules, or negotiated business terms.calculation_or_form_collapse: a worksheet, covenant, tax, support, or finance-like form was not handled table-first.issue_spotting_coverage_collapse: discovery, diligence, counterparty review, or issue spotting lacked an exhaustive row-by-row matrix.
Required Closure Sweep
Before final output:
- Build a requirement ledger from the instructions, matter documents, playbooks, requested filenames, and requested output format.
- Mark each requirement as
included,omitted,not applicable, orconflict. - Resolve every
omittedorconflictrow before finalizing. - Run a one-miss audit for headings, defined terms, party names, dates, jurisdictions, thresholds, notice mechanics, exceptions, schedules, exhibits, signature blocks, citations, and caveats.
Weak-Area Scaffolds
- Long drafts: create clause inventory, defined-term ledger, cross-reference ledger, section-to-requirement reconciliation, and schedule/exhibit/signature closure before prose polish.
- Calculations/forms: extract inputs into a table, record governing formula, units, dates, periods, thresholds, and reconcile every output field.
- Issue spotting: create one row per source document, request, objection, clause, counterparty mark, or issue before deduplication.
- Final criterion closure: when the work product is close, ask what single criterion a grader would still mark missing; verify every instruction bullet, playbook rule, counterparty position, requested category, filename, and output-format obligation is explicitly represented or ruled out with evidence.
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.
- 2mo ago First seen · 99 lines · 46 tokens per session scan A 2faf2b39ebfc
fairy-tale-legal-feedback is a skill published in the GitHub repository bonginkan/fairy_tale (19 stars, last pushed 25d ago), licensed Apache-2.0. It adds 46 tokens to every session and 892 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 2026-08-30.
fairy-tale-legal-feedback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fairy-tale-legal-feedbackbonginkan/fairy_tale | Skill | 19 | 25d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |