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 richkuo/rk-skills --skill fable-validate-fableplangit clone --depth 1 https://github.com/richkuo/rk-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/richkuo/rk-skills/fable-validate-fableplan)<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-fableplan/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/richkuo/rk-skills/fable-validate-fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-fableplan.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 | $0.00062 | $0.01540 |
| Opus 5 | $0.00031 | $0.00770 |
| Sonnet 5 | $0.00012 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
fable-validate-fableplan 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-validate-fableplan
Chain fable-validate → (conditional) update issue → fableplan into one autonomous run, and stop there: Fable 5.1 validates the issue, the main agent fixes the issue description if needed, and Fable 5.1 plans the implementation. The vetted plan is posted to the issue as a comment. Nothing is built.
This is fable-validate-fableplan-loop with the implementation stage removed — the head of that chain is identical (same validation, same scope gate, same issue edits, same unconditional Fable plan), but the handoff to work-on-issue-loop is dropped. Reach for this when you want the issue fact-checked, corrected, and planned so a human (or a later run) can decide what to do with the plan. When the plan should be built and driven through review in the same run, use fable-validate-fableplan-loop instead.
Do not skip or reorder the chain. Validation gates planning; a plan built on refuted claims is wrong. There is no sanctioned skip: every step runs, and only the "wait for the user's reply" moments are replaced by the decision rules in the cited steps.
Input
Same defaults as fable-validate: issue URL, #<N> / <N> / owner/repo#N, or nothing (defaults to the latest open issue in the current repo).
Steps
Follow fable-validate-loop steps 1 through 4 with the changes below, then run this skill's step 5 in place of fable-validate-loop's steps 5 and 6:
Step 1 (fable-validate): also keep the verdict block and the validation report in the scratchpad; step 4 passes them to the planner. It produces the standard verdict block:
**#<N>: Update issue description? <Yes|No>** · Complexity: <score>/100 — Capability <k> (Risk <r>, Uncertainty <u> — <driver>); Volume <v> (Scope <s>, Coupling <c>, Verification <x>) · fableplan: <yes|no> · Scope: <OK | too large — split/umbrella/narrow>
Step 2 (scope gate): the same four STOP conditions apply; the cost here is a wasted or wrong plan rather than a wrong PR:
| Condition | Action |
|---|---|
Scope: too large (split / umbrella / narrow flagged) |
STOP. Report the disposition and proposed parts — splitting is a human call. |
| Architecture marked ❌ Infeasible | STOP. Report the infeasibility and the "Optimal direction" note. |
| A merged PR already implements the fix | STOP. Report the PR and the close/repurpose recommendation. |
| An open PR is already addressing the issue | STOP. Report the overlapping PR; supersede/join/wait is a human call. |
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 Changed · +4 tokens per session 3197386f6bba
- 11d ago First seen · 55 lines · 58 tokens per session scan A fe783e665a94
fable-validate-fableplan is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,540 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 2026-08-30.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
arming-thought
A Chinese-language routing guide built around checking facts before drawing conclusions. It helps select other methods for tasks such as investigation, decision-making, review, and long-term planning.