Borrowing it
Nothing to install: this file belongs to unbound-force/gaze. 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/unbound-force/gaze/main/.opencode/skill/speckit-workflow/SKILL.mdgit clone --depth 1 https://github.com/unbound-force/gazeWrote 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/unbound-force/gaze/speckit-workflow)<a href="https://agentmods.dev/skills/unbound-force/gaze/speckit-workflow"><img src="https://agentmods.dev/badge/skills/unbound-force/gaze/speckit-workflow/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/unbound-force/gaze/speckit-workflow"><img src="https://agentmods.dev/badge/skills/unbound-force/gaze/speckit-workflow.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 | $0.00038 | $0.01121 |
| Opus 5.5 | $0.00015 | $0.00448 |
| Sonnet 5.5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
speckit-workflow 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 2mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speckit Workflow — Swarm Skill
This skill teaches you (the Swarm coordinator) how to work
with Speckit's pre-decomposed task lists. When a tasks.md
file exists for the active feature, it is the authoritative
decomposition — do NOT re-decompose via CASS.
When This Skill Applies
Check for a tasks.md file in the active spec directory:
- Look for
specs/NNN-*/tasks.mdrelative to the project root (Speckit strategic workflow) - Look for
openspec/changes/*/tasks.md(OpenSpec tactical workflow)
If tasks.md exists, follow the instructions below. If no
tasks.md exists, proceed with standard CASS decomposition.
Reading tasks.md
Phase Structure
Tasks are organized into numbered phases:
## Phase 1: Setup
## Phase 2: Foundational
## Phase 3: User Story 1 (P1)
## Phase 4: User Story 2 (P1)
...
## Phase N: Polish
Map each phase to a Swarm epic. Phase 1 becomes epic "Setup", Phase 2 becomes epic "Foundational", etc.
Task Format
Each task follows this format:
- [ ] T001 [P] [US1] Description with file path
- Checkbox
- [ ]: Uncompleted task.- [x]: Done. - Task ID
T001: Sequential identifier [P]marker: This task can run in parallel with other[P]tasks in the same phase (they touch different files). Tasks WITHOUT[P]are sequential.[US1]label: Maps to User Story 1 from the spec. Use as cell metadata when creating Swarm cells.- Description: What to do and which file to modify.
Phase Dependencies
- Setup and Foundational phases MUST complete before any User Story phases begin.
- User Story phases may run in parallel if they are marked as independent in the Dependencies section of tasks.md.
- Polish phase runs after all User Story phases.
Creating Swarm Work Items
- Read the full
tasks.mdto understand all phases.
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.
- 2mo ago First seen · 142 lines · 38 tokens per session scan A 0497febe00e5
speckit-workflow is a skill published in the GitHub repository unbound-force/gaze (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 1,121 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 2026-08-31.
speckit-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| speckit-workflowunbound-force/gaze | Skill | 4 | yesterday | Apache-2.0 | A | 38 | OpenCode |
| PlannerRazaib-khan/ForgeWeave | Skill | 1 | 4mo ago | MIT | A | 21 | Claude Code |
| planning-and-task-breakdownvanja-emichi/a0_agent_skills | Skill | 5 | 3mo ago | MIT | A | 56 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| developmentfengshao1227/ccg-workflow | Skill | 6.0k | 4d ago | MIT | A | 41 | Claude Code |
| debugging-executionsn8n-io/n8n | Skill | 210k | yesterday | none | A | 86 | Claude Code, Codex |
| tencent-docsUnicomAI/wanwu | Skill | 2.4k | 14d ago | Apache-2.0 | A | 209 | Claude Code, Codex |