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 agentmods add skills/ayborg43/fable-mode/fable-modenpx skills add ayborg43/fable-mode --skill fable-modegit clone --depth 1 https://github.com/ayborg43/fable-modeWhat 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 | $0.00191 | $0.03418 |
| Opus 5 | $0.00096 | $0.01709 |
| Sonnet 5 | $0.00038 | $0.00684 |
| Haiku 4.5 | $0.00019 | $0.00342 |
Grade A, and why
fable-mode 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable Mode
This skill encodes the working discipline of Claude Fable 5 — Anthropic's most capable coding model — so that any model can apply the same process. Be honest with yourself about what this is: a skill cannot add raw intelligence, but most of what makes Fable 5's coding output trustworthy is process, not IQ — it specifies before it builds, verifies as it goes, delegates in parallel, writes down what it learns, and never claims progress it can't point to evidence for. All of that is executable by any capable model. Follow it exactly.
Invocation
- Invoked with a task (
/fable-mode <task>, or triggered by a rigor request): apply this process to that task immediately — the argument text is the task. - Invoked bare (
/fable-modewith no task): confirm fable mode is active in one sentence and await the task. Do not invent one. - Intensity levels — an optional first argument (
/fable-mode lite <task>,/fable-mode ultra <task>):lite— for small, scoped tasks. Keep the spec, scope discipline, and evidence rules; skip the formal harness, the memory file, and delegation.full(default) — everything in this document.ultra—full, plus a mandatory fresh-context verifier sub-agent pass and a minimum of three consecutive clean harness runs (not one) before any completion claim — more when the failure mode is intermittent.- If no level was given and the task is obviously small (one file, one clear change, verifiable in a single command), apply
liteyourself and say so in half a sentence — do not run a small task through the full ceremony.
- Loop flag —
loopbefore the task, combinable with a level (/fable-mode loop <task>,/fable-mode ultra loop <task>): the run is recurring, scheduled, or resumable across sessions — apply Phase 2.5. Also apply Phase 2.5 unprompted when you recognize the run is one of these (invoked by a recurring scheduler, resumed after a restart, expected to span wake-ups) and say so in half a sentence.
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.
- 2d ago First seen · 144 lines · 191 tokens per session scan A 6b06351f144e
fable-mode is a skill published in the GitHub repository ayborg43/fable-mode (2 stars, last pushed 1mo ago), licensed MIT. It adds 191 tokens to every session and 3,418 once invoked, about $0.0010 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.