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 commands/valsecchi75/project-scaffolder/taskgit clone --depth 1 https://github.com/valsecchi75/project-scaffolderWhat 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 | $0.00027 | $0.00685 |
| Opus 5 | $0.00014 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
task 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/task
Assign a task to the Cortex — the project's AI project leader. Cortex classifies the work, finds or generates the right skills, delegates to a specialist, runs QA and user testing, and propagates learning back to the skill network.
Usage
/task <description>
/task --priority <low|medium|high> <description>
/task --skip-persona <description>
/task --skill <skill-name> <description>
Flags
| Flag | Effect |
|---|---|
--priority high |
Reduces max iterations to 2. QA focuses on correctness only (skips Karpathy compliance for speed). |
--skip-persona |
Skip Persona-Lab user simulation (for backend/infra tasks with no UX impact). |
--skill <name> |
Force a specific skill instead of letting Cortex auto-classify. |
--no-phase-doc |
Skip the Execution Doc gate (conscious choice, logged as [GATE-SKIPPED]) |
--design / --no-design |
Force or skip the design gate (design-first skill). The gate is mandatory anyway on the first task of a phase and on Complex tasks. |
| (none) | Cortex auto-classifies and decides the full pipeline. |
Examples
/task Implement Android home screen widget showing total monthly spend
/task --priority high Fix the renewal date calculation bug for annual subscriptions
/task --skip-persona Refactor database schema to add notes column
/task --skill qs-flutter-patterns Add pull-to-refresh on the subscription list
What happens
- Step 0 gate — Cortex verifies that
docs/phases/PHASE-{N}-execution.mdexists for the current phase. Missing and no--no-phase-doc→ the task is refused; run/phase-docfirst. - Cortex classifies — determines domain, complexity, required skills
- Skill lookup/generation — finds existing skill or generates one on-demand
- Design gate — first task of a phase and Complex tasks go through a design dialogue (design-first skill): questions one at a time, 2-3 approaches, your approval. The approved design may revise scaffold rules (
[DESIGN-REVISION]) - Specialist executes — subagent implements with the approved design + skill as context
- QA verifies — ephemeral subagent checks correctness + Karpathy compliance
- Persona-Lab tests — simulates 3 end-user profiles (unless skipped)
- Synapse propagates — updates skills with lessons learned, propagates to connected skills
- Closes loop — updates priorities, daily log, reports to user
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.
- 2d ago First seen · 57 lines · 27 tokens per session scan A 9763ac00e0b2
task is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 685 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.