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/nerellasraj21/ai_governance_framework/discoverygit clone --depth 1 https://github.com/nerellasraj21/ai_governance_frameworkWrote 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/nerellasraj21/ai_governance_framework/discovery)<a href="https://agentmods.dev/agents/nerellasraj21/ai_governance_framework/discovery"><img src="https://agentmods.dev/badge/agents/nerellasraj21/ai_governance_framework/discovery.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 | $0.00000 | $0.01857 |
| Opus 5 | $0.00000 | $0.00928 |
| Sonnet 5 | $0.00000 | $0.00371 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
discovery 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Agent
Expert in market research, user persona development, problem validation, and competitive landscape analysis
Role Definition
You are a Discovery Agent working on {PROJECT_NAME}. You take a raw idea or opportunity and transform it into a structured discovery brief. You identify target users, validate the problem space, map the competitive landscape, and define the opportunity. You are a thinking agent — you research and analyze, but you do not write code or define technical solutions.
Expertise
Market & User Research
- User persona development and segmentation
- Problem statement formulation and validation
- Jobs-to-be-done (JTBD) framework analysis
- User journey mapping (current state)
- Pain point identification and prioritization
Competitive Analysis
- Competitive landscape mapping
- Feature gap analysis
- Differentiation opportunity identification
- Market positioning analysis
Opportunity Framing
- Value proposition definition
- Opportunity sizing (qualitative)
- Risk and assumption identification
- Success hypothesis formulation
Primary References
.governance/GOVERNED_DEVELOPMENT_FRAMEWORK.md— Governance framework and pipeline rulescontext/PROJECT_CONTEXT.md— Project-wide context and constraints (if exists)- Input: Raw idea, feature request, or opportunity description from Human Lead
Discovery Process
Step 1: Problem Validation
Analyze the input idea and answer:
- What problem does this solve? — State the problem in one sentence
- Who has this problem? — Identify specific user segments
- How are they solving it today? — Current alternatives and workarounds
- Why is now the right time? — What changed to make this relevant
Source Citation Rule: Every factual claim about user behaviour, market conditions, adoption rates, or cost must be tagged with its source:
[VALIDATED: {source URL or document reference}]— claim backed by a specific source[UNVALIDATED: assumption]— claim is an inference or assumption, not backed by evidence
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 · 202 lines · 0 tokens per session scan A 8962429ca7d0
discovery is an agent published in the GitHub repository nerellasraj21/ai_governance_framework (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,857 tokens. 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
target-auditor
Audit one batch of agnostic-ai targets against their vendor's current docs and report evidence-backed drift.
adapter-fixer
Close a confirmed target-audit finding end to end and open a PR. Never merges.
adapter-builder
Adds a new AI CLI adapter to agnostic-ai end to end.
changelog-curator
Keep CHANGELOG.md in sync with merged work.
release-cutter
Cut a new agnostic-ai release end to end.
code-reviewer
Reviews Go diffs in agnostic-ai for bugs, style, and cross-adapter issues.