epct

A structured development method with four stages: explore the codebase, plan the change, write the code, and test it.

In plain words
What is it for?
It helps investigate existing code, create an implementation and testing plan, carry out the change, and verify the result.
Why use it?
It reduces missed dependencies, edge cases, project conventions, and tests during feature work.

Command

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 commands/fusengine/agents/epct
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 478 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 $0.00020 $0.00478
Opus 5 $0.00010 $0.00239
Sonnet 5 $0.00004 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash 60b13718065d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epct 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.

plugins/ai-pilot/commands/epct.md · 90 lines

What it actually says

EPCT: Explore-Plan-Code-Test

Execute systematic development methodology:

Phase 1: EXPLORE

Use explore-codebase to understand relevant parts of the system

Goals:

  • Identify where changes need to be made
  • Understand existing patterns and conventions
  • Map dependencies and impacts
  • Locate relevant tests

Deliverable: Exploration summary with affected components

Phase 2: PLAN

Use research-expert to validate approach against best practices

Goals:

  • Design solution following project patterns
  • Identify edge cases and error handling
  • Plan test strategy
  • Estimate impact and complexity

Deliverable: Implementation plan with step-by-step approach

Plan Format:

### Implementation Steps
1. [Component A]: [Changes needed]
2. [Component B]: [Changes needed]
3. [Tests]: [Test cases to add]

### Edge Cases
- [Case 1]: [Handling approach]
- [Case 2]: [Handling approach]

### Testing Strategy
- Unit tests: [What to test]
- Integration tests: [Scenarios]
- Manual testing: [Steps]

Phase 3: CODE

Implement the solution:

  1. Follow the plan step-by-step
  2. Maintain existing code style and patterns
  3. Add inline documentation for complex logic
  4. Create/update tests alongside code

Phase 4: TEST

Comprehensive validation:

  1. Run Linters:

    bun run lint
    eslint .
    prettier --check .
    
  2. Run Tests:

    bun test
    pytest
    
  3. Manual Testing:

    • Execute test plan scenarios
    • Verify edge cases
    • Check error handling
  4. Final Verification:

    Use sniper to ensure 0 linter errors

Deliverable: Tested, validated code ready for commit

Arguments:

  • $ARGUMENTS specifies the feature/task to implement

Example Usage:

  • /epct Add user profile editing → Full EPCT for feature
  • /epct Fix authentication bug → EPCT for bug fix
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. yesterday First seen · 90 lines · 20 tokens per session scan A 60b13718065d

Subscribe to this mod's changes

epct is a command published in the GitHub repository fusengine/agents (25 stars, last pushed 28d ago), licensed MIT. It adds 20 tokens to every session and 478 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 2026-08-30.