phase-audit

A review step for a completed phase made up of several smaller changes, called slices. A fresh reviewer checks every slice against the specification and checks that they work consistently together.

In plain words
What is it for?
It helps audit all changes in a multi-part phase before sign-off, especially when a large specification is being marked complete.
Why use it?
Reviewing each change separately can miss problems between changes or gradual departures from the original plan.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fusebase-dev/fusebase-flow/phase-audit
Any agent
npx skills add fusebase-dev/fusebase-flow --skill phase-audit
Clone the repo
git clone --depth 1 https://github.com/fusebase-dev/fusebase-flow

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.01027
Opus 5 $0.00046 $0.00513
Sonnet 5 $0.00018 $0.00205
Haiku 4.5 $0.00009 $0.00103

Measured 2d ago against content hash 7410f5a2f6d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-audit 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.

.agents/skills/phase-audit/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Audit

Style: Mode-B-lite.

Purpose

After a phase of multiple slices is implemented, run an independent audit (a fresh sub-agent with no implementation bias) over EVERY slice — verifying each against the spec/decisions and checking cross-slice consistency — before the phase is signed off. Catches drift that per-slice, in-session review misses.

When to invoke

  • A phase with 2+ slices is implemented and awaiting sign-off.
  • Operator says "audit the phase", "review all slices", "independent audit", "did we miss anything across the phase".
  • Before flipping a large spec DRAFT→DONE.

Do not invoke when

  • Single change / single diff → use code-review.
  • Security-specific concern → use security-permissions-review.
  • Phase not yet implemented (nothing to audit).
  • A trivial one-slice phase (per-slice review suffices).

Required inputs

Input Where it lives If missing
Spec + decisions docs/specs/<slug>/ stop; cannot audit without the target
Slice list + SHAs docs/specs/<slug>/tasks.md derive from git log of the phase range
Implemented diff git diff <phase-start>..HEAD stop

Procedure

  1. Scope. Identify the phase's slices and their commit range from tasks.md / git log.
  2. Delegate (independent). Per flow-skills/task-delegation/SKILL.md, spawn a fresh sub-agent (read-only) so the audit is unbiased by the implementing session.
  3. Per-slice audit. For each slice: does the diff satisfy its acceptance criteria; cite file:line; flag gaps, scope creep, TODOs, missing tests.
  4. Cross-slice consistency. Check slices don't contradict each other, duplicate logic, or leave a seam (shared types, interfaces, data shape).
  5. Drift vs spec/North Star. Confirm the phase as a whole still matches the spec/decisions and docs/north-star.md if present.
  6. Consolidate. Produce one report: per-slice verdicts + cross-slice findings, split into blockers vs non-blockers, each with file:line evidence.
  7. Adversarial pass (optional). For high-risk phases, have the sub-agent try to refute its own "looks good" verdicts before reporting.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 2d ago First seen · 90 lines · 92 tokens per session scan A 7410f5a2f6d1

Subscribe to this mod's changes

phase-audit is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 92 tokens to every session and 1,027 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

adobe-express-core

Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.

Sandgrouse/adobe-express-dev-skill · 50 tokens

adobe-express-monetization

Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.

Sandgrouse/adobe-express-dev-skill · 44 tokens

adobe-express-spectrum-ui-ux

Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…

Sandgrouse/adobe-express-dev-skill · 70 tokens

adobe-express-cors-and-backend

Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…

Sandgrouse/adobe-express-dev-skill · 92 tokens

adobe-express-document-manipulation

Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.

Sandgrouse/adobe-express-dev-skill · 43 tokens

adobe-express-oauth-authentication

Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.

Sandgrouse/adobe-express-dev-skill · 50 tokens