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 skills add alonf/specrew --skill specrew-capacity-planninggit clone --depth 1 https://github.com/alonf/specrewWrote 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/skills/alonf/specrew/specrew-capacity-planning)<a href="https://agentmods.dev/skills/alonf/specrew/specrew-capacity-planning"><img src="https://agentmods.dev/badge/skills/alonf/specrew/specrew-capacity-planning.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 | $0.00031 | $0.00720 |
| Opus 5 | $0.00015 | $0.00360 |
| Sonnet 5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
specrew-capacity-planning 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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specrew-capacity-planning
Type: Planning Skill
Schema: v1
Status: Active planning method
Purpose
Analyze in-scope requirements, produce a taskable effort model, and make overcommit visible before the plan is approved.
When to Use
- During the Planning ceremony
- When re-planning after needs-rework or abandonment
- For deferral and what-if sequencing decisions
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
| spec_requirements | array | Yes | List of requirements to plan for this iteration |
| iteration_config | object | Yes | Config from .specrew/iteration-config.yml |
| iteration_config.capacity_per_iteration | number | Yes | Max effort units for this iteration |
| iteration_config.effort_unit | string | Yes | Unit of effort measurement |
| iteration_config.overcommit_threshold | float | Yes | Ratio for overcommit warning |
| role_assignments | array | Yes | Available roles from .specrew/role-assignments.yml |
| historical_velocity | number? | No | Average effort per iteration for calibration |
Process
- Break each requirement into executable work and enabling work
- Estimate effort per task and by phase:
- planning
- discovery/spikes
- implementation
- review
- expected rework
- Assign tasks to role owners, not individual nicknames
- Calculate total effort and compare it to configured capacity
- If over capacity:
- rank deferral candidates from the lowest-priority requirement slices first
- identify the requirement impact of each deferral
- surface whether approval is needed
- Return a plan-ready task list plus a capacity narrative
Outputs
| Output | Type | Description |
|---|---|---|
| tasks[] | array | Decomposed task list |
| tasks[].id | string | Task identifier |
| tasks[].title | string | Task description |
| tasks[].requirement_ref | string | Requirement this task implements |
| tasks[].effort | number | Estimated effort in the configured unit |
| tasks[].owner | string | Assigned role name |
| total_effort | number | Sum of all task efforts |
| capacity_status | enum: ok, warn, error | Capacity check result |
| capacity_message | string? | Warning or error message if not ok, including explicit defer guidance |
| suggested_deferrals[] | array? | Lowest-priority tasks/requirements to defer if overcommitted |
| phase_baseline[] | array | Planned effort by phase for retro comparison |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 83 lines · 31 tokens per session scan A 92d5419e4eff
specrew-capacity-planning is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 720 once invoked, about $0.0002 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.