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/beyondnetcode/evolith_arch32/discovery-agentsgit clone --depth 1 https://github.com/beyondnetcode/evolith_arch32What 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 | $0.00000 | $0.00597 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
discovery-agents 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 yesterday.
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
Intake and Discovery Agents (Phases 00 and 01.1)
Bilingual Navigation: Versión en Español
The following agents support the Architecture Planning Gate (Phase 00). Each agent follows the Agent Update Quality rule: scope, inputs, outputs, constraints, handoff, validation checklist, and audit output format.
| Agent | Scope | Inputs | Outputs | Handoff To |
|---|---|---|---|---|
| Architecture Plan Interpreter | Analyze raw requirements to generate an Architecture Plan for Gate 0 evaluation | Raw business requirement prompt, ADRs, blueprints | Architecture Plan Draft (JSON/YAML) | OPA Evaluation Engine / Human Approver |
| Business Discovery Agent | Extract problem statement, value proposition, and business context from stakeholders or prompts | Business trigger, stakeholder interviews, market context | Discovery Knowledge Brief (draft) | Product Framing Agent |
| Product Framing Agent | Structure domain context, identify actors, and define scope boundaries | Knowledge Brief, domain knowledge, product vision | Knowledge Brief (validated), Capability Map (seed) | Capability Modeling Agent |
| Capability Modeling Agent | Decompose domain into capabilities with priority and dependencies | Validated Knowledge Brief, domain model, stakeholder priorities | Capability Map | Epic Discovery Agent |
| Epic Discovery Agent | Map capabilities to epic candidates with MoSCoW priority and size estimation | Capability Map, business priorities, technical constraints | Epic Candidate Matrix | Story Slicing Agent |
| Story Slicing Agent | Create minimal story seeds from epic candidates with acceptance criteria drafts | Epic Candidate Matrix, user roles, behavioral expectations | Story Seed Bank | Acceptance Criteria Agent |
| Acceptance Criteria Agent | Validate and refine acceptance criteria for story seeds, ensure testability | Story Seed Bank, domain rules, quality standards | Story Seed Bank (refined) | Architecture Discovery Agent |
| Architecture Discovery Agent | Identify technical constraints, ADR candidates, spikes, and enablers | Knowledge Brief, Capability Map, technical context | Architecture constraints section, Decision Candidates | Discovery Gate Agent |
| Discovery Gate Agent | Validate knowledge sufficiency against adoption level requirements | All 01.1 artifacts, adoption level, quality checklist | Discovery Readiness Gate (PASS/CONDITIONAL/FAIL) | Next phase (Ballpark / Backlog / Design) |
| Knowledge Drift Agent | Detect when code changes occur without corresponding knowledge updates | git diff, knowledge artifact ownership globs, Discovery Context Pack | Drift signals (FYI, not blocking) | Current phase owner |
Common constraints for all Discovery Agents:
- Must not create epics, stories, or backlog items — only knowledge artifacts
- Must maintain traceability IDs across all outputs
- Must produce bilingual outputs when repository requires it
- Must not introduce vendor or framework dependencies
- Must declare adoption level in all artifacts
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.
- yesterday First seen · 26 lines · 0 tokens per session scan A 860d3be5fd95
discovery-agents is an agent published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 597 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
implementer
Milestone executor. Use when a planner has handed off a milestone, a fix list, or itemsremaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.
planner
Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.
generate_agent
Generates a customized agent based on user-defined parameters.
workflow-conductor
Agent "workflow-conductor" from s977043/PlanGate, covering workflow conductor, iron law, 起動前提（router が capability preflight 済み / task-0072）, common rationalizations and 8つの役割.
ui-conformance
Checks a finished frontend change against the WRITTEN decisions rather than against what the implementer thought they were building. Reads the decision documents and the checkable requirement lines, drives a real browser through the Playwright MCP server, and reports pass or fail per requirement with the measured…
implementer
PlanGate exec フェーズのタスク実装エージェント。workflow-conductor から委譲されたタスクを TDD で実装し、完了報告する。タスクごとに新規起動される使い捨てエージェント。.