implement-change

A workflow for carrying out an already reviewed software-change plan while limiting edits to the files and steps listed in that plan.

In plain words
What is it for?
It helps resume planned work, implement steps in order, write regression tests, check the branch, and record verification results. A regression test checks that a previously broken behavior stays fixed.
Why use it?
It keeps implementation aligned with the agreed scope and requires the named tests and verification evidence before the work is considered 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/matheuspavaneli/workbench/implement-change
Any agent
npx skills add matheusPavaneli/workbench --skill implement-change
Clone the repo
git clone --depth 1 https://github.com/matheusPavaneli/workbench

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 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 $0.00051 $0.00840
Opus 5 $0.00026 $0.00420
Sonnet 5 $0.00010 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured yesterday against content hash 6fbf4e1341b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-change 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 yesterday.

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.

skills/implement-change/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

implement-change

python "${CLAUDE_PLUGIN_ROOT}/lib/wb.py" <args>

Steps

  1. Read the plan's own slices, not the whole document: sdd get <KEY> --section steps and --section files. No sdd.json? Run plan-change first. A failed audit blocks every command here by design — fix the plan, do not work around it.

    Picking work back up mid-way? status <KEY> says which planned files are already changed and what is left, without re-reading the plan.

  2. Check where you are. flow show reports the branch this work starts from, whether the current branch is protected, and any validation branch the commits will later be carried onto. flow start <KEY> --title "..." prints the branch name and base to use.

  3. Implement one step at a time, in order, touching only the listed files. Follow the repo's existing patterns. Nothing tidied, renamed or upgraded along the way: the plan's file list is the scope, and it was reviewed.

  4. Write the tests the plan named. sdd get <KEY> --section tests. Each entry says what must hold — assert that, not that a function was called. A regression test must fail without the fix; check that it does.

  5. Check the scope. impl check <KEY> after each step or two. It lists planned files as changed or pending, other for a file another audited plan claims, and overlap where two plans claim one file. It fails only on a file no audited plan accounts for.

  6. Verify. impl verify <KEY> runs the plan's verify commands and writes .workflow/<KEY>/evidence.md. It refuses anything that is not a known test, build or lint runner — run those yourself and say so.

  7. Report honestly. If verification fails, say so with the failing line. Fix the code, never the evidence.

Do not re-run sdd audit to confirm your work: it checks the plan, not the code. Re-run it when you change the plan — that now passes, reporting which citations have drifted. impl check and impl verify are the checks for this stage.

Read the full file on GitHub · 72 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. yesterday First seen · 72 lines · 51 tokens per session scan A 6fbf4e1341b2

Subscribe to this mod's changes

implement-change is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 840 once invoked, about $0.0003 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

integration-rule-engine

A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.

aozyildirim/Agena · 67 tokens

stale-ticket-triage

Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.

aozyildirim/Agena · 57 tokens

azure-devops

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…

sanjay3290/ai-skills · 105 tokens

apple-container

Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…

sanjay3290/ai-skills · 146 tokens

atlassian

Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…

sanjay3290/ai-skills · 96 tokens

google-calendar

Interact with Google Calendar - list calendars, view events, create/update/delete events, and find free time. Use when user asks to: check calendar, schedule a meeting, create an event, find available time, list upcoming events, delete or update a calendar event, or respond to meeting invitations. Lightweight…

sanjay3290/ai-skills · 76 tokens