easd-specify

A guide for writing or revising an EASD specification, a reviewable description of a software change grounded in repository documents and saved project state.

In plain words
What is it for?
Use it when an EASD run is in its intent or authoring stage and you need to produce a contract for review. It is not for implementing the change.
Why use it?
It helps keep the specification tied to the repository’s current rules and evidence instead of relying on memory or informal planning.

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

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,073 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 $0.00048 $0.01073
Opus 5 $0.00024 $0.00536
Sonnet 5 $0.00010 $0.00215
Haiku 4.5 $0.00005 $0.00107

Measured 2d ago against content hash 2fdb333ba86b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

easd-specify 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-specify/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specify an EASD run

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. Read the tracked knowledge-base index.yaml, specs/, features/, architecture/, and reference/ plus any existing project documentation named by repository instructions. Do not copy or move existing docs into EASD 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.

Turn persisted Intent into a grounded contract that the user can review. This skill supplies procedure, not lifecycle authority: repository authorization, run state, submission, and acceptance remain enforced by EvoFlux.

State gate

Re-read the persisted run state and latest visible revision from current EASD context on every invocation; do not continue from chat memory alone. intent may be explored but must enter authoring before submission. authoring permits one typed draft submission. In draft, show proposed changes against the current revision and leave replacement/new-revision control to the user. An accepted or active run belongs to planning or execution, not this Skill.

Work from evidence

  1. Read the run Intent and every applicable AGENTS.md in the authorized repository scope.
  2. Inspect current feature, architecture, and reference docs, then the owning source, configuration, migrations, and focused tests. Treat plans as proposals and code/tests as current-state evidence when reverse-engineering. Keep multi-repository provenance explicit as repository:path and never infer a path from conversation shorthand.
  3. Scan for high-impact ambiguity in scope, actors/permissions, state and data, critical journeys, loading/error/recovery, concurrency, security/privacy, integration, compatibility, observability, and completion signals. Ask a concise clarifying question before selecting an option that can change product behavior; do not interrogate the user about low-impact details.
  4. Produce a provider-neutral specification with outcome, goals, non-goals, source references, repository-qualified impact targets, constraints, compatibility/security boundaries, risk tier, planned verification commands, and stable observable ACs with per-AC evidence policies. Recommend direct only for a low-risk single-boundary change; otherwise recommend planned and cite the conditions requiring Plan. The user reviews this choice with the Spec.
  5. Make provenance and uncertainty visible. Do not invent files, commands, behavior, or confidence unsupported by the inspected repository.
  6. Self-review the draft for contradictions, placeholders, untestable language, uncovered critical flows, scope drift, and ACs without concrete evidence. For every applicable flow, cover happy behavior plus relevant error, authorization, domain-invariant, recovery/concurrency, and cross-context behavior. Fix those gaps before submission or expose them as unresolved questions; do not add irrelevant scenarios merely to fill a checklist.

Read the full file on GitHub · 100 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 · 100 lines · 48 tokens per session scan A 2fdb333ba86b

Subscribe to this mod's changes

easd-specify is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,073 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

kane-cli

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…

LambdaTest/kane-cli · 159 tokens

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

release

Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI…

Sma1lboy/rove · 155 tokens

hyperframes-cli

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, or remove-background, or when troubleshooting the…

Sma1lboy/rove · 101 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