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 Team-Deepiri/deepiri-axiom --skill efficient-fablegit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/efficient-fable)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/efficient-fable"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/efficient-fable/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/team-deepiri/deepiri-axiom/efficient-fable"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/efficient-fable.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00804 |
| Opus 5.5 | $0.00017 | $0.00322 |
| Sonnet 5.5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
efficient-fable 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Efficient Fable
Use Claude Fable as the orchestrator, architect, synthesizer, and final judge. Use cheaper subagents for token-heavy research, coding, testing, and summarization that do not need Fable's full judgment.
Source: BuilderIO/skills (efficient-fable). MIT.
For the same pattern on any frontier model (not Fable-specific), use efficient-frontier.
Where Fable shines
Reserve Fable for:
- Decomposing ambiguous work into clean parallel slices
- Architecture, product, and safety tradeoffs
- Reading conflicting subagent reports and deciding what matters
- Integrating partial implementations into one coherent plan
- Final review, risk assessment, and user-facing synthesis
Delegation pattern
- Name the expensive-token risk: large repo search, long logs, broad docs, or repetitive edits
- Split independent work into subagents before reading everything yourself
- Use cheaper models for research scans, inventory, search summaries, narrow bug hunts, browser/testing passes, test output reduction, and bounded code edits
- Ask subagents for concise evidence: files, line refs, commands run, diffs, uncertainties, and stop conditions
- Spend Fable tokens on the decision layer: compare results, resolve conflicts, choose the path, review the final patch
Prefer parallel subagents when slices are independent. Keep blocking or highly coupled work local.
Handoff packets
Write delegated prompts as if the subagent has no chat context. Include:
- Repo path and exact objective
- In-scope / out-of-scope files, packages, or surfaces
- Evidence format: files, line refs, commands, diffs, failures, uncertainty
- Verification commands or flows, plus what success looks like when known
- Stop conditions: code ≠ prompt assumption, command fails after a reasonable retry, or out-of-scope files needed → stop and report
Vetting delegated work
Treat subagent reports as leads, not facts. Before high-impact use, a PR, or telling the user work is done: reopen cited files, confirm line refs/failures, review the final diff against the task. Lighter agents gather signal; Fable keeps truth-judgment.
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.
- 11d ago First seen · 75 lines · 42 tokens per session scan A a17b1ed9f762
efficient-fable is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 804 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 2026-10-26.
efficient-fable compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| efficient-fableTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 42 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |