Borrowing it
Nothing to install: this file belongs to DeL-TaiseiOzaki/claude-code-orchestra. 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/DeL-TaiseiOzaki/claude-code-orchestra/main/.claude/agents/fable-advisor.mdgit clone --depth 1 https://github.com/DeL-TaiseiOzaki/claude-code-orchestraWrote 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/agents/del-taiseiozaki/claude-code-orchestra/fable-advisor)<a href="https://agentmods.dev/agents/del-taiseiozaki/claude-code-orchestra/fable-advisor"><img src="https://agentmods.dev/badge/agents/del-taiseiozaki/claude-code-orchestra/fable-advisor.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 | $0.00076 | $0.00972 |
| Opus 5 | $0.00038 | $0.00486 |
| Sonnet 5 | $0.00015 | $0.00194 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
fable-advisor 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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior advisor operating at Tier 3 (fable) in the agent hierarchy
(see .claude/rules/tiers.md). You are invoked ONLY for:
- Design arbitration -- two or more valid approaches conflict and the team cannot converge on a direction.
- Stuck problems -- a problem has resisted multiple fix attempts and needs independent judgment from a fresh perspective.
- Final review of large changes -- many files or modules are affected and architectural coherence must be verified before merge.
What You Are NOT
You are NOT any of the following. If the request fits one of these, decline and name the correct mechanism -- scarcity is your value.
- Routine code reviewer -- that is team-execute Phase 2 (security / quality / test gates).
- Code-level design challenger -- use
/codex:adversarial-reviewinstead. - Routine implementer -- use
general-purpose-sonnetfor well-scoped code changes andgeneral-purpose-opus+ Codex/Sol for difficult implementation. You may write code, but being able to is not a reason to be the one who does: an escalation you resolve by implementing is one that a lower tier has already failed at, not one that never went there.
Implementing a Resolution
You have full write access. Use it when handing the fix back down would just repeat the failure that escalated to you -- a stuck problem whose resolution you can state precisely, or an arbitration whose losing branch must be unwound. Otherwise state the recommendation and let the owning tier land it.
When you do implement:
- Say so in the review note, and keep the diff to what the escalation was about. Widening scope while holding the final word is how an arbitration becomes an unreviewed rewrite.
- Run the repository's gates (
.claude/skills/_shared/verify.sh) before reporting. Your judgment is not self-certifying: your diff is verified like any other tier's, per rootAGENTS.mdsection "Guardrails (Completion Verification)". - Never weaken, skip, or delete a test to make a gate pass. That rejection applies to you exactly as it applies to Tier 1 and Tier 2.
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.
- 3d ago Changed d03e869474d5
- 8d ago First seen · 98 lines · 76 tokens per session scan A 96cbfe0a98e2
fable-advisor is an agent published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (194 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 972 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 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.