Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Justinmendezai/The-Adam-Reponpx agentmods add skills/justinmendezai/the-adam-repo/slice-to-tasksWrote 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/justinmendezai/the-adam-repo/slice-to-tasks)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/slice-to-tasks"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/slice-to-tasks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/slice-to-tasks"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/slice-to-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.02129 |
| Opus 5 | $0.00031 | $0.01064 |
| Sonnet 5 | $0.00012 | $0.00426 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
slice-to-tasks scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://localhost:3000/api/<slice-feature> >/dev/null How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slice-to-tasks
Turn an approved plan/plan.md into a folder of slice briefs. Each slice is one Composer 2 subagent's worth of work. Each slice is independently shippable when its dependencies are met.
Definition of a slice
A vertical slice:
- Touches as much of the stack as needed to deliver one user-visible behavior or one acceptance criterion.
- Has explicit
paths_in_scopeandpaths_out_of_scope. - Has an explicit
acceptanceblock — what tests must pass and what runtime behavior must hold. - Has a runnable verifier (
slices/<id>/verify.shor an inlineverifyone-liner) that exits0when ACs hold. This is the done-signal the Tier-1orchestrate-buildloop re-runs independently — distinct from the full unit/E2E suite. - Declares its dependencies on other slices by id.
- Is small enough for a Composer 2 subagent to complete in one go (< ~500 LOC change in most cases). Larger slices declare a
sub_tasks:block so the Tier-2dispatch-managercan fan out sequentially.
Workflow
1. Read
plan/plan.mdplan/CONTEXT.mdpacket/PACKET.mdsuccess_criteria
2. Draft slices
For each success criterion, identify the smallest chunk of work that proves it. Then split anything still too big. Group foundation work (types, schemas, scaffolding) into early slices that others depend on.
Aim for 3–10 slices per build. More than that is usually a sign you're slicing horizontally (by layer) instead of vertically (by behavior).
2b. Mock-first; one terminal live slice
Default slicing policy (minimize mid-run operator gates):
- Build slices use mocks/stubs for OAuth, DNS, Stripe, GSC, and other live integrations. Verifiers must pass against mocks in CI/local.
- Defer real credentials, taste judgment, and SME sign-off to one terminal slice at the end of the DAG:
integration-live # human_gated: true, depends_on: [<all feature slices>]
That slice's verifier may require live env; everything else stays mock-green. Items that still need operator action append to agent-control/human-queue.md — the build loop does not pause.
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.
- 12d ago First seen · 176 lines · 62 tokens per session scan A 227022ec62e1
slice-to-tasks is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,129 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…