easd-review

easd-review is a skill for Claude Code, Codex from evoelsewhere/evoflux. It costs 44 tokens per session (873 once invoked), scanned A, original, Apache-2.0.

A read-only review process for checking an EASD implementation against its accepted specification, acceptance criteria, and ownership boundaries. EASD refers to the project’s documented implementation process described in its repository.

In plain words
What is it for?
Reviewing completed changes, checking repository documents and specification versions, and identifying missing contracts, stale revisions, or changes that violate the agreed requirements.
Why use it?
It helps find implementation problems independently instead of relying only on the developer’s summary or tests.

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/evoelsewhere/evoflux/easd-review
Any agent
npx skills add evoelsewhere/evoflux --skill easd-review
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for easd-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/evoelsewhere/evoflux/easd-review.svg)](https://agentmods.dev/skills/evoelsewhere/evoflux/easd-review)
Your own site
<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/easd-review"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/easd-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 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 $0.00044 $0.00873
Opus 5 $0.00022 $0.00436
Sonnet 5 $0.00009 $0.00175
Haiku 4.5 $0.00004 $0.00087

Measured 4d ago against content hash 1b9937c919ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

easd-review 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 4d 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.

.evoflux/skills/easd-review/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review an EASD implementation

Repository contract

Read .evoflux/easd/config.json and its rules_file before phase work. Treat the injected EASD context as the authoritative current Run; when the owning runtime is accessible, corroborate it under runtime_directory. An isolated worktree intentionally has no checkout-local runtime copy. Confirm the common specs/ revision and Run-local accepted snapshot have the same hash. Inspect affected living features/, architecture/, and reference/ documents plus existing project docs at their original paths. Repository documents are the shared source of truth. Stop on a missing tracked contract, stale hash, generation conflict, or unavailable injected runtime; never reconstruct authority from chat memory or a stale database-only projection. Review is mandatory for both direct and planned; independence remains risk-driven.

Act as an independent, read-only challenger. Review the actual integrated change against the exact accepted spec hash; do not treat the implementer's handoff or test summary as the source of truth.

State gate

Re-read the run, accepted Spec hash, delivery flow, assigned review ACs, integrated revision/diff, optional accepted Plan hash, and current evidence. Review only while the run is reviewing; active waits for the user's Run review action and verifying belongs to the next Skill. If an applicable hash or reviewed snapshot changes during the pass, invalidate the verdict and restart against the new snapshot; do not patch an old verdict forward.

Review protocol

  1. Confirm the run ID, accepted hash, assigned ACs, risk tier, affected repositories/paths, and whether reviewer independence is required. If you authored the change and independence is required, stop and request a fresh reviewer.
  2. Read the accepted contract and inspect the integrated diff and owning files directly. Review the integrated revision, not an abandoned worktree or a parent summary.
  3. Trace each in-scope AC through observable behavior, implementation, tests, interfaces, and current documentation. Check applicable happy, error, authorization, domain-invariant, recovery/concurrency, and cross-layer paths.
  4. Audit responsibility boundaries and dependency direction. Flag changes outside accepted impact targets, hidden coupling, undeclared shared ownership, or a local task that silently became cross-layer work.
  5. Cite every finding with an AC or contract reference plus repository path and line/source evidence. Separate blocking correctness/security/scope findings from non-blocking suggestions; drop claims that cannot be sourced.
  6. Return an explicit per-AC verdict and list the evidence inspected, checks not run, uncertainty, and required remediation. After fixes, review the new diff afresh rather than assuming the prior finding was resolved.

Read the full file on GitHub · 75 lines

Files

What ships with it

1 file 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.

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. 4d ago First seen · 75 lines · 44 tokens per session scan A 1b9937c919ca

Subscribe to this mod's changes

easd-review is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 44 tokens to every session and 873 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.