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 skills add byx-darwin/gitflow-cli --skill gf-issue-decomposegit clone --depth 1 https://github.com/byx-darwin/gitflow-cliWrote 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/byx-darwin/gitflow-cli/gf-issue-decompose)<a href="https://agentmods.dev/skills/byx-darwin/gitflow-cli/gf-issue-decompose"><img src="https://agentmods.dev/badge/skills/byx-darwin/gitflow-cli/gf-issue-decompose/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/byx-darwin/gitflow-cli/gf-issue-decompose"><img src="https://agentmods.dev/badge/skills/byx-darwin/gitflow-cli/gf-issue-decompose.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.01251 |
| Opus 5.5 | $0.00025 | $0.00500 |
| Sonnet 5.5 | $0.00012 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
gf-issue-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 28d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gf-issue-decompose
Decomposes a document into vertically sliced, falsifiable, ordered tickets.
MUST use gf, NOT gh — gh breaks GitLab/GitCode.
Preconditions
command -v gf·gf auth status- A document to decompose
When to Use
| English | 中文 | Context |
|---|---|---|
| break this spec into issues | 把规格拆成 Issue | document, no tickets |
| decompose the requirement | 拆解需求 | many deliverables |
| split into tickets with dependencies | 拆票并标依赖 | ordering matters |
| file one issue | 提一个 Issue | does NOT fire |
Trigger Keywords
| English | 中文 |
|---|---|
| decompose, break down | 拆解, 拆分 |
| slice into tickets | 切票 |
| blocked by, dependency order | 阻塞, 依赖序 |
When NOT to Use
| Scenario | Use Instead |
|---|---|
| One ticket, interactive | /gf-issue-create |
| Judging an Issue's quality | /gf-issue-review |
| Labelling the backlog | /gf-issue-triage |
| Edit / close / comment | /gf-issue |
Procedure
0 — Floor. Fits in one context window → do not split. Emit one ticket.
1 — Slice. One narrow path per ticket, through every layer. Slicing by layer is the
default error: a horizontal layer is not a vertical slice. Ticket one is a
tracer bullet. → references/vertical-slice.md
2 — Falsify. Name what observation would prove it false; fire it at the
base commit, where it must be red (not-found and compile errors count). Reject one
already true on base, one observing what belongs to another ticket, one that
restates the requirement. → references/falsifiable-criteria.md
3 — Order. Declare Blocked by: #N when this ticket cannot go green before the
other merges; the criterion stays here. Create in dependency order. Wide refactors
split expand → migrate → contract. → references/dependency-edges.md
4 — Confirm. Before creating anything, ask and wait:
- granularity — ticket count right?
- demo path — what does each ticket demonstrate?
- edges — blockers real, order acyclic?
What ships with it
3 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.
- 28d ago First seen · 143 lines · 62 tokens per session scan A ed9d665e5f60
gf-issue-decompose is a skill published in the GitHub repository byx-darwin/gitflow-cli (3 stars, last pushed 22d ago), licensed MIT. It adds 62 tokens to every session and 1,251 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…