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/codebygarv/ai-skills/task-breakdown-assistantnpx skills add codebygarv/Ai-skills --skill task-breakdown-assistantgit clone --depth 1 https://github.com/codebygarv/Ai-skillsWhat 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 | $0.00045 | $0.00481 |
| Opus 5 | $0.00023 | $0.00241 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
task-breakdown-assistant 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Break one task/ticket down into concrete, sequenced subtasks small enough to just start on. Deliberately atomic and single-task scoped — for whole-project phasing and cross-team dependencies, see Project Planner instead.
When to Use
- A single ticket/task feels too large or vague to start on directly.
- Estimating a task requires understanding its real sub-steps first.
- Handing a task to someone else and want to leave them a concrete starting checklist.
Differs from Project Planner: that skill produces phases/milestones for a multi-task project; this skill produces the subtask checklist for one task within that project.
What to Analyze / Do
- Clarify the actual definition of done for the task, if it's not already explicit.
- Break into subtasks small enough that each one is independently completable in a short sitting, not another multi-day task in disguise.
- Sequence them — note which subtasks block others, and which can happen in any order.
- Flag the riskiest/most uncertain subtask — the one most likely to reveal a surprise or take longer than expected — and suggest tackling it earlier rather than last.
- Keep scope honest — if breaking the task down reveals it's actually two or three separate tasks bundled together, say so explicitly rather than forcing a single flat checklist.
Output Format
- Definition of done, restated briefly.
- Numbered subtask checklist, with dependency notes ("after subtask 2") where relevant.
- One line flagging the riskiest subtask and why.
- If scope creep was found, a explicit note recommending the task be split.
Avoid
- Producing subtasks so granular they're just narrating obvious steps ("open the file," "save the file").
- Producing subtasks so broad they're just smaller versions of "do the whole task."
- Silently absorbing a task that's actually multiple unrelated tasks — flag it instead of forcing a single checklist.
What ships with it
2 files 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.
- 2d ago First seen · 38 lines · 45 tokens per session scan A c5ced315baa4
task-breakdown-assistant is a skill published in the GitHub repository codebygarv/Ai-skills (24 stars, last pushed 13d ago), licensed MIT. It adds 45 tokens to every session and 481 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
bun-api
Bun runtime API reference for TypeScript scripts. Covers Bun.file(), Bun.write(), Bun.$() shell, Bun.spawn(), Bun.Glob, Bun.env, bun:sqlite, Bun.sql() for PostgreSQL/MySQL via DATABASEURL, Bun.s3 for S3-compatible storage, Bun.redis for Redis/Valkey, Bun.Archive for tarballs, Bun.Image image processing, Bun.WebView…
bun-cli
Bun CLI reference for package management, script running, testing, bundling, and compilation. Covers bun install/add/remove/update, bun run, bun test, bun build, bunx, bun patch, bun audit fix, bun dedupe, bun prune, bun why, bun pm, bun repl, bunfig.toml, bun.lock, workspace catalogs, isolated installs and the global…
deps-upgrade
Validate JavaScript/TypeScript dependency upgrades after an interactive or manual update. Establish the real delta from git, detect peer/engine/type conflicts, extract breaking changes, migrations and adoptable features from release notes, assess held-back or seemingly unused packages, and run verification gates.…
git-pr
PR and MR workflows for GitHub (gh) and GitLab (glab). Creation, review comment handling, thread resolution, review state queries, merging, cost-aware bot review rounds (GitHub: Copilot, CodeRabbit), and Copilot code review configuration (rulesets, custom instructions, billing). Use when creating PRs/MRs, addressing…
git-project
GitHub Projects (v2) setup and management via gh CLI + GraphQL: organize a repo's issues into epics with native sub-issues, drive a board Status flow (Todo -> In Progress -> Done), set Project Priority, classify with native issue Types (Task/Bug/Feature) instead of labels, scope work with milestones (incl. resolving…
git-ci
CI/CD status queries for GitHub Actions (gh) and GitLab CI (glab). Check pipeline status, failing jobs, workflow runs, job logs, and merge readiness. Use when checking CI status, debugging build failures, viewing job logs, watching pipeline progress, or configuring gh/glab CI read-only allowlists. Not for PR workflows…