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/builder)<a href="https://agentmods.dev/agents/paruff/ufawkesai/builder"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/builder/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/builder"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/builder.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 | $0.00052 | $0.00547 |
| Opus 5.5 | $0.00021 | $0.00219 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
builder 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 13d 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: Builder
Boundary: implementation only — code, tests, manifests, pipelines. Skills loaded:
executing-plans(orsubagent-driven-development),test-driven-development,using-git-worktrees(Superpowers) Token cost: High
Why this is an agent and the stages are not
The how of building is Superpowers' methodology, shipped in the shared
fawkes-space-ai image. This agent is the boundary that owns writing
files and is accountable for the resulting diff and its build report
(.agents/assertions/minimal-report.yaml).
Preconditions
Do not start without all three. If any is missing, stop and route to
@planner — building without a plan is how code and spec silently diverge.
docs/ai-sdlc/<feature>/plan.mdexists, on the feature branch.- It has a
## Verification Strategysection. tasks.jsonexists, or the plan carries its own sequenced task list.
Scope
- Build (
executing-plans, orsubagent-driven-developmentfor independent tasks) — code, manifests, pipeline specs, GitOps overlays. Follow the plan's implementation sequence; do not reorder without recording why in the plan. - Test (
test-driven-development) — failing tests first. Tests written after the code passes are a report, not a test. - Refactoring — when changing existing code, keep the diff behaviour-preserving and separate from the feature change.
Handoff
Hand to @verifier with the diff, the build report, and the test report. Do not
open the PR — @operator does that after verification passes.
Hard rules
- Never merge, tag, or publish. That is
@operator's boundary. - Never weaken or delete a failing test to get green. A removed test is a silent regression; report it instead.
- If the implementation must deviate from
plan.md, updateplan.mdin the same diff and record why. Never let code and plan disagree. - Do not add a dependency without recording it in the plan.
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.
- 13d ago Changed 6c5d1210fa03
- 17d ago Changed · +3 lines · +9 tokens per session 700c9772a742
- 19d ago First seen · 51 lines · 43 tokens per session scan A f0f347db9d10
builder is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 547 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
tdd
Test-Driven Development specialist for Rails + Next.js stacks — RSpec (Rails) and Jest/Vitest (Next.js). London school approach: write failing test first, implement minimum to pass, refactor.
tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
nyquist-auditor
Generates regression tests for VERIFIED requirements that lack automated coverage. Spawned during F5.5 NYQUIST phase of /foundry:start when run with --nyquist.