/agent-estimation

Agent Work Estimation Skill

Problem

AI coding agents systematically overestimate task duration because they anchor to human developer timelines absorbed from training data. A task an agent can complete in 30 minutes gets estimated as "2-3 days" because that's what a human developer forum post would say.

Solution

Force the agent to estimate from its own operational units — tool-call rounds — and only convert to human wallclock time at the very end.

Core Units

A Round is the atomic unit. It maps directly to one iteration of:

1. Agent reasons about what to do
2. Agent writes/edits code
3. Agent runs the code or a test
4. Agent reads the output
5. Agent decides if it needs to fix something (if yes → next round)

Estimation Procedure

When asked to estimate a task, follow these steps in order:

Step 1: Decompose into Modules

Break the task into functional modules. Each module should be independently buildable and testable. Ask yourself: "What are the distinct pieces I would build one at a time?"

Step 2: Estimate Rounds per Module

For each module, estimate the number of rounds using these anchors:

Key calibration rules:

• If you can generate the code in one shot and it will likely run → 1 round
• If you'll need to generate, run, see an error, and fix → 2-3 rounds
• If the library/framework has sparse docs and you'll be guessing → 5+ rounds
• If it involves platform permissions, OS-level APIs, or environment-specific behavior the user must manually verify → add 2-3 rounds

Step 3: Assign Risk Coefficients

Each module gets a risk coefficient that inflates its round count:

Step 3.5: Construct Waves (Optional — for parallel / multi-agent scenarios)

If the task will be executed by multiple agents or the user asks for fastest completion:

1. Map dependencies: For each module, list which other modules it depends on
2. Group into waves:
   • Wave 1: All modules with zero dependencies
   • Wave 2: Modules whose dependencies are all in Wave 1
   • Wave N: Modules whose dependencies are all in previous waves
3. Note agent count: How many agents can run in parallel within each wave

Skip this step for:

• Single-agent sequential execution
• Projects with < 3 modules
• Tightly coupled modules where parallelism gains are negligible

Step 4: Calculate Totals

Sequential mode (single agent, default):

Module effective rounds = base rounds × risk coefficient
Project rounds = Σ(module effective rounds) + integration rounds
Integration rounds = 10-20% of base total (for wiring modules together)

Wave mode (multi-agent):

Wave duration = max(effective rounds of modules in wave)
Project rounds = Σ(wave durations) + coordination rounds + integration rounds
Coordination rounds = 2-3 rounds upfront (contract definition between agents)

Step 5: Convert to Wallclock Time

Only at the very end, convert to human time:

Wallclock time = project rounds × minutes_per_round

Default minutes_per_round = 3 minutes (includes agent generation time + user review time).

Adjust this parameter based on context:

• Fast iteration, user barely reviews → 2 min/round
• Complex domain, user carefully reviews each step → 4 min/round
• User needs to manually test (mobile, hardware, permissions) → 5 min/round

Output Format

Always output the estimation in this exact structure:

### Task: [task name]

#### Module Breakdown

| # | Module | Base Rounds | Risk | Effective Rounds | Notes |
|---|--------|------------|------|-----------------|-------|
| 1 | ...    | N          | 1.x  | M               | why   |
| 2 | ...    | N          | 1.x  | M               | why   |

#### Summary

- **Base rounds**: X
- **Integration**: +Y rounds
- **Risk-adjusted total**: Z rounds
- **Sequential wallclock**: A – B minutes (at N min/round)

**Wave Execution** (if applicable):
- Wave 1: [modules] → max M rounds
- Wave 2: [modules] → max M rounds
- Coordination overhead: +C rounds
- **Parallel wallclock**: A – B minutes (at N min/round, K agents)
- **Speedup vs sequential**: ~X%

#### Biggest Risks
1. [specific risk and what could blow up the estimate]
2. [...]

Anti-Patterns to Avoid

These are the failure modes this skill exists to prevent:

1. Human-time anchoring: "A developer would take about 2 weeks..." → NO. Start from rounds.
2. Padding by vibes: Adding time "just to be safe" without specific risk rationale → NO. Use risk coefficients.
3. Confusing complexity with volume: 500 lines of boilerplate ≠ hard. One line of CGEvent API ≠ easy. Estimate by uncertainty, not line count.
4. Forgetting integration cost: Modules work alone but break together. Always add integration rounds.
5. Ignoring user-side bottlenecks: If the user must manually grant permissions, restart an app, or test on a device, that's extra round time. Adjust minutes_per_round, don't add phantom rounds.
6. Assuming parallelism is free: Multi-agent wave execution has coordination cost (contract definition, conflict resolution). Always add coordination rounds.

Calibration Reference

Here are example projects with known round counts to help calibrate:

See references/calibration-examples.md for detailed examples across project types.

Eval Prompts

See evals/evals.json for test cases to validate estimation accuracy.