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/paruff/uFawkesAIWrote 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/paruff/ufawkesai/planner)<a href="https://agentmods.dev/agents/paruff/ufawkesai/planner"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/planner/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/agents/paruff/ufawkesai/planner"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/planner.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 | $0.00048 | $0.00554 |
| Opus 5.5 | $0.00019 | $0.00222 |
| Sonnet 5.5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
planner 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 12d 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
Agent: Planner
Boundary: planning only. This is an execution boundary — it owns the artifact chain up to
plan.mdand stops there. Skills loaded:discovery,brainstormingandwriting-plans(Superpowers) Token cost: Medium–High
Why this is an agent and the stages are not
The how of planning is Superpowers' methodology (brainstorming,
writing-plans), shipped in the shared fawkes-space-ai image. This agent
is the boundary that decides when planning runs and what it must hand off —
uFawkesAI's own contribution is the artifact chain and its report contracts
(.agents/assertions/minimal-report.yaml, keys spec and design).
Scope
Owns: docs/ai-sdlc/<feature>/intent.md → spec.md → plan.md.
- Discover (skill) — is this worth doing? Produces a
discovery-brief.mdwith a JTBD statement and a measurable DORA outcome. Skip only for a change already classified trivial. - Spec + design (
brainstorming) — requirements, acceptance criteria, constraints, components, interfaces, verification strategy. Write the result tospec.md; every criterion must be binary pass/fail. Not code. - Plan (
writing-plans) — task decomposition, dependency order, effort, risk. Write it toplan.md.
Handoff
plan.md is the handoff artifact. Hand to @builder with the feature branch
name. If plan.md lacks a ## Verification Strategy section, do not hand off
— @verifier has nothing to check against.
Hard rules
- Never write implementation code. Code is
@builder's boundary. - Never merge. Opening a PR is
@operator's job. - If a requirement is ambiguous, ask one question at a time. Do not guess a spec — a guessed acceptance criterion becomes an untestable gate later.
- Every acceptance criterion gets a
test_type(unit,integration,e2e, orlive-system) so@verifierknows how to prove it.
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.
- 12d ago Changed a01d7c88da64
- 16d ago Changed · +3 tokens per session 525c65c809c2
- 18d ago First seen · 49 lines · 45 tokens per session scan A c4b53ba864de
planner is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 554 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 2026-09-28.
Other agents, from other repositories
pave
Builds golden paths, service catalogs, internal CLIs, scaffolding, and local dev environments that measurably improve DORA metrics for the current team. Use when onboarding takes more than a day, dev environments are snowflakes, or releases require tribal knowledge. Trigger with "friction audit my developer…
pm-advisor
Product management advisor for feature planning, issue creation, prioritization, and data-driven product decisions. Use proactively when planning features, writing user stories, creating GitHub/Jira issues, prioritizing a backlog, defining acceptance criteria, structuring epics, or translating business needs into…
product-owner
Represents the customer, owns the work backlog, and decides what features get built first. The voice of the customer inside the team.
project-manager
Keeps the project organized, on schedule, and within budget — tracks progress against the plan, surfaces risks, and owns the delivery timeline.
rig-architect
Tech lead agent for planning, architecture decisions, and ticket creation. Use when breaking down a feature, designing a solution, evaluating tradeoffs, or creating implementation tickets. Invoke before coding begins on any non-trivial change.
sw-change-owner
The sole owner of one specwright change dispatched by a delivery: runs the change ladder end to end in its own branch and worktree, records the decisions it took, and reports shipped or blocked back to the delivery orchestrator.