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 orenluxy/fable-method --skill merge-quizgit clone --depth 1 https://github.com/orenluxy/fable-methodWrote 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/orenluxy/fable-method/merge-quiz)<a href="https://agentmods.dev/skills/orenluxy/fable-method/merge-quiz"><img src="https://agentmods.dev/badge/skills/orenluxy/fable-method/merge-quiz.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 | $0.00078 | $0.00661 |
| Opus 5 | $0.00039 | $0.00331 |
| Sonnet 5 | $0.00016 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
merge-quiz 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Quiz
Purpose: after a long session, the user's mental model of the changes is a map that has drifted from the territory. Merging on a drifted map is how production incidents happen. The quiz forces the map to be re-synced before the merge button exists.
Procedure
-
Generate the change report as a single self-contained HTML file. If subagents are available, delegate the mechanical inventory (diff stats, file list, test run, notes import) to the
report-builderagent (sonnet) and build the report from its skeleton — the risk register and the quiz remain yours. If an externalstoplosstool is on PATH, run its report and include the numbers. Report sections:- Summary: what was built, in 5 lines max.
- Change inventory: every file touched, grouped by subsystem, with one line per file on what changed and why.
- Behavior changes: what a user/consumer of this system will experience differently. This section matters more than the file list.
- Risk register: the 3 changes most likely to break something, and how to verify each.
- Decisions & Deviations: imported from IMPLEMENTATION_NOTES.md if it exists.
-
Append the quiz at the bottom of the report: 5–8 questions testing whether the user actually understands the changes. Mix of:
- "What happens now when X?" (behavior)
- "Why was Y chosen over Z?" (decisions)
- "Which file would you edit to change W?" (territory knowledge)
- At least one question about a deviation, if any exist. Questions must be answerable only by someone who understands the changes — not by pattern-matching the report's summary.
-
Grade strictly. The user answers in chat. A wrong or fuzzy answer means: explain the correct answer with a pointer to the relevant code, then re-ask a variant. Do not proceed to merge steps until all answers are solid.
-
Only after a clean pass: provide the merge/deploy commands or perform them if asked.
Calibration
- Session touched < ~50 lines in familiar territory: skip the quiz, offer a 3-line summary instead. The gate exists for long sessions, not for typo fixes. Say explicitly that you're skipping it and why.
- Production systems (databases, payment, live servers): the quiz is mandatory regardless of size, and the risk register must include a rollback plan.
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 · 39 lines · 78 tokens per session scan A 5786528b52ab
merge-quiz is a skill published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 661 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
ln-63-release-publisher
Prepares and publishes an explicitly requested tagged GitHub release. Not for ordinary commits, package publication, or announcements.
ln-64-community-announcer
Drafts or publishes fact-checked GitHub Discussions announcements for project updates. Not for release creation or issue responses.
pr-creator
Creates or updates GitHub PRs with house-style titles and bodies, issue linking, repository templates, and draft state. Use when asked to "create a PR", "rewrite the PR description", or "polish this PR". For code fixes use tidy; for CI and review threads use pr-babysitter; for npm releases use autoship.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…