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.
git clone --depth 1 https://github.com/duolahypercho/fusion-fableWrote 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/commands/duolahypercho/fusion-fable/fusion-plan)<a href="https://agentmods.dev/commands/duolahypercho/fusion-fable/fusion-plan"><img src="https://agentmods.dev/badge/commands/duolahypercho/fusion-fable/fusion-plan/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/commands/duolahypercho/fusion-fable/fusion-plan"><img src="https://agentmods.dev/badge/commands/duolahypercho/fusion-fable/fusion-plan.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 | $0.00040 | $0.00646 |
| Opus 5 | $0.00020 | $0.00323 |
| Sonnet 5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
fusion-plan 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 10d 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.
What it actually says
Invoke the fusion-plan skill on the task below. Run the full OMC-integrated flow:
- Requirements — pick the mode FIRST (Step 0 of SKILL.md):
- Non-interactive (default during plan execution, inside a sub-agent, or
--no-interview): do NOT interview, do NOT call AskUserQuestion, do NOT auto-chain omc-plan. Derive requirements from existing context (story docdocs/stories/STORY-*.md, the flagged section of the larger.omc/plans/*.md, and the task args) as the seed. If context is insufficient, stop and report what's missing — never block on an unanswerable question. - Interactive (a human is present, typed
/fusion-plandirectly): run OMC's real interview viaSkill("oh-my-claudecode:omc-plan")on the task verbatim (no--consensus; auto-detect interview vs direct) → initial plan in.omc/plans/<slug>.md. Capture that path as the seed; do not let OMC auto-execute.
- Non-interactive (default during plan execution, inside a sub-agent, or
- Deepen with the panel (3 rounds, seeded): each round, ONE Opus 4.8 panelist (Agent subagent,
model: opus) and ONE GPT-5.5 panelist (codex exec, high effort) independently critique-and-improve the current plan IN PARALLEL and BLIND. Round 1 seeds from the OMC plan (so every interview requirement is preserved); rounds 2–3 seed from the previous synthesis. After each round YOU (Opus 4.8) judge both (Consensus / Contradictions / Partial / Unique / Blind spots) and synthesize one tighter plan. Stop early onNO_MATERIAL_CHANGE(round ≥ 2). Ifcodexis missing, fall back to two Opus 4.8 panelists per round. - Write back: the synthesized plan must be concise but content-dense (no padding) and is written
back to the SAME
.omc/plans/<slug>.mdin OMC standard format, preserving all gathered requirements. - Handoff (offer, don't auto-run execution): quality gate via
/omc-plan --review .omc/plans/<slug>.md, then/teamor/ralphon approval.
Follow skills/fusion-plan/SKILL.md exactly. Do not edit OMC's own skills — integrate only through the
.omc/plans/*.md artifact and by invoking omc-plan.
Task: $ARGUMENTS
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.
- 10d ago First seen · 32 lines · 40 tokens per session scan A bafc1924df37
fusion-plan is a command published in the GitHub repository duolahypercho/fusion-fable (471 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 646 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.