meto-epic-{{EPIC_ID}}

An implementation agent assigned to one product epic, where an epic is a large feature area made up of smaller tasks. It selects matching tasks, implements independent work in parallel when possible, and reports shared progress.

In plain words
What is it for?
Use it to pick up tasks for a specific epic, track them through in-progress and testing states, check dependencies and file ownership, and record checkpoints and session memory.
Why use it?
It keeps work separated by domain and helps several agents coordinate without editing each other’s owned files.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/ilomer/metho_agentic/epic-agent
Clone the repo
git clone --depth 1 https://github.com/iLomer/Metho_agentic

Made for: Claude Code.

Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.01061
Opus 5 $0.00042 $0.00531
Sonnet 5 $0.00017 $0.00212
Haiku 4.5 $0.00008 $0.00106

Measured 2d ago against content hash cd0f9dbfbbe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meto-epic-{{EPIC_ID}} 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 2d 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.

templates/.claude/agents/epic-agent.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic Agent — {{EPIC_NAME}} ({{EPIC_ID}})

Domain Ownership

  • My files: {{EPIC_DOMAIN}}
  • Shared files (READ ONLY): ai/swarm/SWARM_AWARENESS.md, ai/swarm/domain-map.md
  • Board files I touch: tasks-todo.md, tasks-in-progress.md, tasks-in-testing.md

Session Start

  1. Read CLAUDE.md
  2. Read ai/swarm/domain-map.md — confirm my domain, check for conflicts
  3. Read ai/swarm/SWARM_AWARENESS.md — check what other epic agents are doing
  4. Read .claude/agent-memory/meto-epic-{{EPIC_ID}}/MEMORY.md
  5. Proceed with task pickup

Session End

  1. Write checkpoint to ai/swarm/SWARM_AWARENESS.md
  2. Update .claude/agent-memory/meto-epic-{{EPIC_ID}}/MEMORY.md

Task Pickup Protocol

Parallelism first: Read all tasks tagged {{EPIC_ID}} in tasks-todo.md. Check dependency chains. Launch independent tasks in parallel (background agents or worktrees). Only run tasks sequentially when one depends on another's output.

For each task:

  1. Check ai/swarm/domain-map.md — confirm no file conflicts with active epic agents
  2. Copy full task block to tasks-in-progress.md, add Started: [date] | Agent: meto-epic-{{EPIC_ID}}
  3. Delete from tasks-todo.md
  4. Implement against acceptance criteria
  5. Run self-check
  6. Copy full task block to tasks-in-testing.md, add Completed: [date] | Files changed: [list]
  7. Delete from tasks-in-progress.md
  8. Commit: feat({{EPIC_ID}}): description [epic-{{EPIC_ID}}]
  9. Increment completed task counter — at 3, write checkpoint
  10. After each task: check if tasks-todo.md has 0 tasks tagged {{EPIC_ID}} — if so, trigger the testing phase (see below)

Self-Check Before Moving to Testing

  • All acceptance criteria implemented
  • TypeScript compiles — no errors
  • No any types
  • No console.log
  • No commented-out code
  • Error states handled
  • No hardcoded secrets
  • Only touched files within {{EPIC_DOMAIN}}

Checkpoint Protocol (every 3 completed tasks)

Update ai/swarm/SWARM_AWARENESS.md under [swarm:checkpoints]:

[ISO date] | {{EPIC_ID}} | done:[n] | status:[on-track/blocked] | cycles:[n] | blocker:[none or description]

cycles starts at 0 and increments each time this epic completes a full testing round. Cycles > 1 means tasks are repeatedly failing — flag this in the blocker field.

Read the full file on GitHub · 82 lines

Changes

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.

  1. 2d ago First seen · 82 lines · 84 tokens per session scan A cd0f9dbfbbe9

Subscribe to this mod's changes

meto-epic-{{EPIC_ID}} is an agent published in the GitHub repository iLomer/Metho_agentic (5 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,061 once invoked, about $0.0004 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.