Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/decompose/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/decompose)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/decompose"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/decompose.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00096 | $0.05986 |
| Opus 5 | $0.00048 | $0.02993 |
| Sonnet 5 | $0.00019 | $0.01197 |
| Haiku 4.5 | $0.00010 | $0.00599 |
Grade A, and why
decompose 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 7d 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decompose — Hierarchical Task Network Goal Decomposition
Breaks compound goals into primitive, executable sub-goals using a recursive HTN-inspired algorithm. Called automatically by /aspirations during the execution loop, or manually for planning.
Parameters
goal_id(required) — The goal ID to decompose (e.g.,g-003-01)--dry-run— Show decomposition plan without writing changes--max-depth N— Override max decomposition depth (default: 4)
Step 0: Load Conventions
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.
Step 1: Load Goal Context
Bash: aspirations-read.sh --active
Find goal by ID in the output (search all aspirations' goals for the goal_id)
Read any files listed in goal.context_needed
Step 1.5: Idempotency Check (fast exit for already-decomposed goals)
Before Step 2's primitiveness test, check whether this goal was decomposed in a prior session. Re-decomposing would duplicate work.
IF goal.status == "decomposed" OR (goal.decomposed_into is a non-empty list):
# Verify at least one child is still live.
Bash: aspirations-read.sh --active (locate children by ID)
# --active filters to status==active aspirations (g-115-2604 parity fix) —
# a child parked in a PAUSED aspiration is invisible to this dump. Before
# concluding a child is gone, fall back to a per-id read of its parent
# aspiration (derive asp-id from the goal-id prefix: g-336-04 -> asp-336):
# Bash: aspirations-read.sh --id <asp-id> (finds paused/any-status parents)
# Only children found in NEITHER read count as missing/terminal.
live_children = [c for c in children if c.status in {pending, in-progress, blocked}]
IF live_children is non-empty:
# No-op — prior decomposition is intact and children are actionable.
# Emit a terminal Bash call and RETURN. Do NOT output any text,
# insight block, table, or summary paragraph after this call.
# Return-protocol rule (.claude/rules/return-protocol.md): text after
# the final Bash kills the autonomous session.
Bash: echo "decompose no-op — g-{id} already decomposed into {N} live children: {child-ids}"
RETURN
# If all children are terminal (completed/expired/skipped), fall through
# to Step 2 for fresh primitiveness evaluation — parent may warrant
# re-decomposition under new constraints.
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.
- 7d ago First seen · 460 lines · 96 tokens per session scan A 6c1cdaba7d3d
decompose is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 5,986 once invoked, about $0.0005 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.