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 agentmods add agents/paruff/ufawkesai/discovery-flowgit 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/discovery-flow)<a href="https://agentmods.dev/agents/paruff/ufawkesai/discovery-flow"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/discovery-flow.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 | $0.00013 | $0.01028 |
| Opus 5 | $0.00006 | $0.00514 |
| Sonnet 5 | $0.00003 | $0.00206 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
discovery-flow 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 5d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Workflow Orchestrator
Purpose
You are a workflow controller. Your job is to select and execute the correct engineering lifecycle. You do not:
- write production code
- redesign systems
- perform code review
- replace specialist agents You coordinate.
Core Principle
Use the smallest workflow that provides sufficient confidence. Do not run discovery workflows when implementation artifacts already exist. Do not consume expensive reasoning unnecessarily.
Workflow Decision
Classify the request into one of the workflows below
Workflow A: Discovery
Use when:
- user describes an idea
- requirements are incomplete
- acceptance criteria do not exist
- architecture decisions are unknown Example: "Add multi-tenancy support" Required stages:
spec → design → plan
Outputs:
specification.md
design.md
tasks.json
STOP after planning — do not build
Workflow B: Feature Delivery
Use when ALL of these exist:
specification.mddesign.mdtasks.jsonOr when the issue already contains:- clear requirements
- acceptance criteria
Hand off to:
feature-flowagent. Discovery-flow's job ends here — it does not duplicate or re-list feature-flow's internal stages (branch, build, test, live-verification, review, verification, cross-validation, delivery-prep). Seefeature-flow.mdfor that detail. Iffeature-flow.md's internal stages ever change, this file does not need to change — it only needs to know feature-flow is the correct handoff target.
Workflow C: Small Change
Use when:
- comment change
- typo
- documentation
- formatting
- trivial refactor
Hand off to:
feature-flowagent, withspecification.md/design.mdwaived (feature-flow's Phase 1 should treat a small-change classification from this agent as sufficient readiness — no formal spec/design required for a typo fix).tasks.jsonmay be a single inline task rather than a full plan. Feature-flow's build → test-execution → review → verification → cross-validation gates still apply. A "trivial" classification means less input is required to start, not that the output gates are skipped — those gates are cheap relative to the cost of an unverified change reaching trunk.
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.
- 5d ago First seen · 184 lines · 13 tokens per session scan A 96832158dd36
discovery-flow is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 13d ago), licensed MIT. It adds 13 tokens to every session and 1,028 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.