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 kzytateishi/spikeee-plugins-marketplace --skill dev-workflowgit clone --depth 1 https://github.com/kzytateishi/spikeee-plugins-marketplaceWrote 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/kzytateishi/spikeee-plugins-marketplace/dev-workflow)<a href="https://agentmods.dev/skills/kzytateishi/spikeee-plugins-marketplace/dev-workflow"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/dev-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/kzytateishi/spikeee-plugins-marketplace/dev-workflow"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/dev-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 | $0.00054 | $0.00801 |
| Opus 5 | $0.00027 | $0.00400 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
dev-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 10d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Workflow — Full Workflow
Run the complete development workflow for $ARGUMENTS.
Execution Mode
Run all steps sequentially. By default, pause after Step 1 (specify) and present the spec to the user for confirmation before proceeding to implementation. Steps 2–5 run automatically, stopping only on gate failures.
Skip the specify confirmation only when the user explicitly requests it (e.g., "確認不要", "skip confirmation", "そのまま進めて").
Workflow
Each step MUST pass its gate condition before proceeding to the next step.
Step 1: /specify → Generate specification + task list
GATE: user confirmation (default, skippable)
Step 2: /implement → Implement tasks from the specification
GATE: all tests, lint, and type checks pass
Step 3: /refactor → Iterative refactoring (3+ rounds)
GATE: all tests, lint, and type checks pass
Step 4: /code-review → Multi-perspective code review
GATE: no Critical or High findings remain
Step 5: /pr-summary → Generate PR description
Gate Failure Handling
If a gate fails, STOP the workflow and fix the issues before proceeding:
- Step 1 confirmation gate: present the spec summary and ask the user to approve, request changes, or abort. If the user requests changes, revise the spec and ask again. Do NOT proceed to Step 2 until the user explicitly approves.
- Step 2/3 gate failure: debug and fix until all tests, lint, and type checks pass
- Step 4 gate failure: fix all Critical and High findings, then re-run
/code-reviewto verify. Do NOT proceed to Step 5 with unresolved Critical or High findings.
Step 1: Specify
Generate a specification document and task list for the feature described in $ARGUMENTS.
Read and follow the full process defined in specify/SKILL.md.
User Confirmation
After generating the spec, present a summary to the user:
- Detected scenario type
- Key design decisions
- Scope (number of tasks, affected files)
- Link to
order.mdandtodo.md
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.
- 10d ago First seen · 95 lines · 54 tokens per session scan A dd9b6ff0f6d1
dev-workflow is a skill published in the GitHub repository kzytateishi/spikeee-plugins-marketplace (5 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 801 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.