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/centminmod/my-claude-code-setup/task-breakdownnpx skills add centminmod/my-claude-code-setup --skill task-breakdowngit clone --depth 1 https://github.com/centminmod/my-claude-code-setupWhat 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 | $0.00177 | $0.02427 |
| Opus 5 | $0.00088 | $0.01213 |
| Sonnet 5 | $0.00035 | $0.00485 |
| Haiku 4.5 | $0.00018 | $0.00243 |
Grade A, and why
task-breakdown 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 3d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Breakdown
Turns a session's per-request breakdown (the deterministic request_units
emitted by session-metrics) into semantic tasks the user actually thinks
in — "added auth", "debugged the cache miss" — and labels each with a verdict.
You do the one thing deterministic code can't: decide which requests belong to
the same task. The script does everything else (cost, turns, tokens, waste
signals, the themed page).
Model. This skill runs on your session's current model. It no longer pins
one (a hard model: pin ran the inline turn on that model, dragging the whole
conversation into that model's context window — on a long session that
overflowed and broke invocation). The grouping + verdict work is
judgement-heavy, so it wants a capable model; for a cheaper run that's still
strong enough, /model sonnet before invoking. Don't drop to Haiku — the
semantic verdicts need the headroom.
Division of labour — do not blur it:
- The export owns the numbers. Every cost / turn / token / waste figure
comes from
request_unitsin the JSON export. You MUST NOT sum money or invent figures —--render-tasksrecomputes all totals from the export. - You own the grouping + labels only. You assign each
request_unit_idto a task, write a short title, a verdict, and a one-line rationale.
Inputs
$ARGUMENTS[0] (optional) = path to a session-metrics JSON export, e.g.
exports/session-metrics/session_<id8>_<ts>.json (session scope is the primary
target; project_*.json also works — units carry a session_id). The export
must contain a request_units array.
If $ARGUMENTS[0] is missing, first generate a session export by invoking the
session-metrics skill (or run its script) for the session of interest with
--output json html, then use the written session_*.json path.
Steps
- Locate the export and the renderer.
- Export:
$ARGUMENTS[0], or the JSON you just generated. - Renderer: the sibling session-metrics skill's script. Resolve its
path (it ships in the same plugin):
- plugin install:
../session-metrics/scripts/session-metrics.py - dev repo:
.claude/skills/session-metrics/scripts/session-metrics.pyUse whichever exists (glob if unsure).
- plugin install:
- Export:
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.
- 3d ago First seen · 183 lines · 177 tokens per session scan A 948ee59d6ebd
task-breakdown is a skill published in the GitHub repository centminmod/my-claude-code-setup (2,614 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 2,427 once invoked, about $0.0009 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
memory-bank
Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…
building-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode…
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
scaffolding-openai-agents
Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming…
tool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.