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 commands/connorrmcd6/vibe-spec/spec-phasesgit clone --depth 1 https://github.com/Connorrmcd6/vibe-specWrote 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/commands/connorrmcd6/vibe-spec/spec-phases)<a href="https://agentmods.dev/commands/connorrmcd6/vibe-spec/spec-phases"><img src="https://agentmods.dev/badge/commands/connorrmcd6/vibe-spec/spec-phases.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 | $0.00035 | $0.00456 |
| Opus 5 | $0.00017 | $0.00228 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
spec-phases scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are running Step 3 of the Vibe-Spec spec-driven workflow: promoting the V1
spec → V2 spec by breaking it into phases. See the vibe-spec skill
(${CLAUDE_PLUGIN_ROOT}/skills/vibe-spec/reference/00-workflow.md) for the phase
conventions.
What to do
-
Read
docs/project-spec.md(the V1 spec from/spec-refine). If it isn't a tool-mapped V1, tell the user to run/spec-refinefirst. -
Break the work into sequential, self-contained phases. Each phase should be a chunk that can be planned, implemented, and verified independently, completable in roughly 1–3 sessions, with clear entry/exit boundaries so no context bleeds between phases. Early phases lay foundation (scaffold, DB, auth); later phases build features and polish.
-
Outline only at this stage — phase name, scope boundaries, and a sentence or two on what each covers. Do not fully design them yet (that's
/spec-plan). -
Append a phase index table to the end of
docs/project-spec.mdand mark the document V2. Use this shape:### Phase Plan | # | File | Scope | |---|------|-------| | 1 | `docs/plans/phase-1-foundation.md` | Project scaffold, data ingestion | | 2 | `docs/plans/phase-2-auth.md` | Auth, onboarding | | 3 | `docs/plans/phase-3-dashboard.md` | Transforms, core dashboard views |
The V2 spec is the final version — V0 and V1 can be discarded. End by telling the
user to run /spec-plan to flesh out the first phase.
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.
- 5d ago First seen · 36 lines · 35 tokens per session scan A cb451ddc2b8f
spec-phases is a command published in the GitHub repository Connorrmcd6/vibe-spec (9 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 456 once invoked, about $0.0002 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 commands, from other repositories
cleanup-repo
When /cleanup-repo is invoked, immediately execute the following steps to analyze, organize, and clean up the repository structure when files are scattered and disorganized.
devops
When /devops is invoked, immediately execute the following steps to create, configure, or manage DevOps infrastructure, CI/CD pipelines, and deployment configurations.
magic-wand
When /magic-wand [issue description] is invoked, immediately execute the following steps to perform a comprehensive, expert-level analysis and fix when standard debugging approaches have failed.
audit-code
When /audit-code [target] is invoked, immediately execute the following steps to analyze code quality, security, and adherence to project standards.
brainstorm
When /brainstorm [topic] is invoked, immediately execute the following steps to collaboratively brainstorm, enhance, and plan new features for the app through an iterative product management workflow.
clean-code
When /clean-code [target] is invoked, immediately execute the following steps to remove redundant code, unused variables, dead code, debug statements, and other technical debt.