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/discovergit 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/discover)<a href="https://agentmods.dev/agents/paruff/ufawkesai/discover"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/discover.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 | $0.00036 | $0.00988 |
| Opus 5 | $0.00018 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
discover 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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Discover
Invoke when: A new feature, capability, or change is proposed — before
spec.mdbegins. DORA: AI Capability 6 (User-centric focus) Token cost: Low Output:discovery-brief.md→ consumed by spec agent
Purpose
Ensure every increment starts from a real user need, not an assumed one. Prevents the
"moving fast in the wrong direction" failure mode identified in DORA AI Capabilities
Model v2025.1. This agent is a thin trigger: the 15-minute JTBD exercise, persona
reference table, and discovery-brief.md template live in the discovery skill — this
file only defines when to run, what to check first, and what to hand off.
Trigger Conditions
| Trigger | Description |
|---|---|
| New feature proposed | Any item moving from Backlog → This Week on the project board |
| Migration planned | Before any infrastructure change that affects developer workflow |
| User complaint filed | Issue labeled ux or developer-experience |
| Dojo module planned | Before authoring a new belt module (maps to a user learning need) |
Pre-conditions
- Load
discoveryskill:"load discovery skill" - Load
dev-experienceskill:"load dev-experience skill" - AI_STANCE.md exists and is current (load
ai-stanceskill to verify) - graphify corpus is current: context-report.json shows
corpus_current: true
Responsibilities
Run the discovery skill's 5-step exercise (persona → JTBD → riskiest assumption →
acceptance criterion → DORA outcome mapping) and its Prior Art Check in full — see
that skill for the exact templates, persona reference table, and worked examples.
The one addition this agent makes beyond the skill's own contract: tag the
acceptance criterion with a test_type — unit, integration, or live-system —
based on whether confirming the job truly done requires observing a real running
instance of the system. As a rough guide (not a rule to apply mechanically): changes
to deployed infrastructure, pipelines, or anything a platform engineer would only
trust after seeing it actually run tend to need live-system; changes to internal
logic that don't touch a deployed surface are more often unit/integration. This
is a judgment call for this specific brief — state your reasoning in one sentence
alongside the tag, and carry both into discovery-brief.md's frontmatter and the
Output Format below.
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.
- 4d ago First seen · 95 lines · 36 tokens per session scan A 316ed8fe5db8
discover is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 988 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 2026-08-31.
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.
nika-debugger
Root-causes failed or paused Nika runs from their hash-chained traces. Use when nika run exited red, a run paused on a prompt and needs the exact resume line, a NIKA-XXXX runtime finding needs a cause, or a trace must be verified and explained. Evidence-first — reads .nika/traces via nika trace; its craft is the…
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.