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/tarekkharsa/agentstack/breakdownnpx skills add Tarekkharsa/agentstack --skill breakdowngit clone --depth 1 https://github.com/Tarekkharsa/agentstackWhat 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 | $0.00025 | $0.00367 |
| Opus 5 | $0.00013 | $0.00183 |
| Sonnet 5 | $0.00005 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
linear_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 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.
What it actually says
Linear Breakdown
Unofficial, agentstack-authored. Not affiliated with or endorsed by Linear.
Use this skill when a Linear issue is too big to ship in one pass and needs to be split into smaller tickets a team can pick up independently.
Workflow
- Read the parent issue end to end. Pull out the user-facing outcome, the acceptance criteria, and any constraints (deadlines, owners, affected areas).
- Decompose by shippable slice, not by layer. Each child ticket should be something that can land and be verified on its own — avoid "backend ticket" + "frontend ticket" pairs that only make sense merged.
- For every child ticket, write:
- a title in imperative voice ("Add X", "Migrate Y"),
- a one-line outcome and explicit acceptance criteria,
- a rough size (S / M / L) — split anything that reads as L,
- dependencies on sibling tickets, if any.
- Order the tickets so the first one delivers value or unblocks the rest. Flag the critical path.
- Link every child back to the parent and keep the parent as the tracking issue.
Conventions
- Prefer 3–7 children. More than that usually means the slices are too thin.
- Each child should be mergeable within roughly a day of focused work.
- Never invent acceptance criteria the parent does not support — ask instead.
When using the Linear MCP, create the parent's sub-issues rather than detached issues, and set the team/project to match the parent so the breakdown stays grouped.
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 · 25 tokens per session scan A 2a247a0d111f
linear_breakdown is a skill published in the GitHub repository Tarekkharsa/agentstack (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 25 tokens to every session and 367 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
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
stack-merge
Bulk-merge a Graphite stack into main via admin-bypass fast-forward push. Replaces the Graphite merge queue for rivet-dev/rivet. Invoke when the user says "merge the stack at ", "ship everything through ", "bulk-merge up to ", "fast-forward main to ", or any request to land multiple stacked PRs at once in one shot.…