easd-verify

A final verification skill for EASD, a project process that checks implemented work against accepted requirements and supporting evidence.

In plain words
What is it for?
Use it after implementation and independent review to assess whether the result meets the accepted EASD specification and to prepare a convergence recommendation.
Why use it?
It catches missing contracts, outdated specifications, conflicting generated work, or insufficient proof before declaring the work complete.

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

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 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 $0.00049 $0.00855
Opus 5 $0.00024 $0.00428
Sonnet 5 $0.00010 $0.00171
Haiku 4.5 $0.00005 $0.00085

Measured 2d ago against content hash 65573796f281, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

easd-verify 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.

.evoflux/skills/easd-verify/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify and prepare EASD convergence

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 knowledge sections and existing project docs without migrating them implicitly. 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. Verify and Converge remain mandatory for both direct and planned.

Challenge the integrated result against the exact accepted specification. This skill helps gather and assess evidence; only the EASD service computes Done.

State gate

Re-read the persisted run detail, accepted revision/hash, AC matrix, missions, evidence, deviations, and convergence state on every invocation. Evaluate only the current accepted hash. Only verifying may perform the final gate; reviewing waits for the user's Run verify action. If already converged, report the existing durable result without duplicating evidence or rerunning convergence. Any other state returns to its owning phase.

Verify claims

  1. Load the accepted run ID/hash, current AC matrix, risk tier, planned commands, missions, evidence, and deviations. Reject stale-spec evidence.
  2. Check three dimensions: completeness of required AC/mission/command/doc coverage; correctness of behavior and scenarios; and coherence of the integrated architecture, interfaces, terminology, and current documentation.
  3. Inspect the integrated result and consume independent easd-review findings where the risk/evidence policy requires them. Execute approved verification missions through EASD-bound delegation so the runtime can persist a fresh, revision-bound CompletionContract even though this phase is read-only. Re-run safe required checks and relevant negative, recovery, authorization, compatibility, smoke/liveness, and cross-layer paths. Read fresh full output and exit status before stating that a command or behavior passed.
  4. Map each result to an AC and its evidence policy. Preserve machine, review, manual, and waiver provenance; never manufacture command IDs, exit codes, revisions, artifact hashes, or reviewer independence.
  5. For cross-layer or critical runs, ensure review is performed by an agent or human independent of the implementation owner and covers the integrated revision rather than an abandoned worktree.
  6. Reconcile adopted EASD features/, architecture/, and reference/ documents, existing project docs, localized Help, and release or migration notes where the accepted behavior requires them. Never move existing docs as an implicit verification side effect.

Read the full file on GitHub · 77 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. 2d ago First seen · 77 lines · 49 tokens per session scan A 65573796f281

Subscribe to this mod's changes

easd-verify is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 49 tokens to every session and 855 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.

Related

Other skills, from other repositories

rove

Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.

Sma1lboy/rove · 56 tokens

E2E Testing Nori Skillsets Subcommands

Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation.

tilework-tech/nori-skillsets · 39 tokens

changelog-generator

Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…

Sma1lboy/rove · 101 tokens

token-saver-config

Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.

ppgranger/token-saver · 37 tokens

issue-review

Triage a copperhead GitHub issue, attempt reproduction, and check it against the spec. Use when the user asks to review an issue, e.g. /issue-review 42 or /issue-review .

copperheadhq/copperhead · 47 tokens

openai-docs

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…

rojim666/SztuCode · 105 tokens