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 skills/nirecom/agents/start-tasknpx skills add nirecom/agents --skill start-taskgit clone --depth 1 https://github.com/nirecom/agentsWhat 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 | $0.00016 | $0.00420 |
| Opus 5 | $0.00008 | $0.00210 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
start-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 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.
What it actually says
Start a task (phase implementation, incident response, or improvement)
Arguments
$TASK_ID - Task identifier (e.g., 3E, 4, incident-xxx)
Project Detection
Determine the docs location based on the current project:
- LangChain projects (langchain-stack, litellm-stack, open-webui-stack, portable-llm-server):
- Docs:
../my-specs-repo/projects/engineering/langchain/
- Docs:
- General projects: Docs:
docs/within the project root
Procedure
- Read project docs (follow path resolution from project detection above):
architecture.md,todo.md(and other existing docs)
- Read the target repo's
CLAUDE.md - Read
.context-private/handoff-phase{$TASK_ID}.md(if exists) - Read
.context-private/completion-phase{prev}.md(if exists — determine prev from todo.md Status Summary or history.md) - Read
ops.md(for incident/infrastructure tasks) - Cross-check handoff against higher-priority documents:
- Priority 1: Project docs (
architecture.md,todo.md,CLAUDE.md) - Priority 2: Previous completion report
- Priority 3: Current handoff
- Priority 1: Project docs (
- If conflicts found, present them to the user before proceeding
- Present a work plan to the user and wait for approval before starting implementation
Rules
- If no handoff document exists, ask the user for task scope
- Never start implementation without presenting the plan first
.context-private/is gitignored — Glob and Grep cannot see it. Usels(Bash) to list files, andReadto read them directly by path.
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.
- yesterday First seen · 43 lines · 16 tokens per session scan A d9e9aecaea1a
start-task is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 420 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…