implement

A workflow for making one focused improvement to a codebase: plan it, implement it, check it, and commit it.

In plain words
What is it for?
Use it for a specific bug fix or roadmap item that affects a limited part of the project.
Why use it?
It gives small changes a clear process and helps ensure they are tested and recorded properly.

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/telus-labs/stagecraft/implement
Any agent
npx skills add telus-labs/stagecraft --skill implement
Clone the repo
git clone --depth 1 https://github.com/telus-labs/stagecraft

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,603 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 $0.00122 $0.01603
Opus 5 $0.00061 $0.00801
Sonnet 5 $0.00024 $0.00321
Haiku 4.5 $0.00012 $0.00160

Measured 2d ago against content hash a76bad6486b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

skills/implement/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement a Change

A four-step workflow for implementing improvements: plan, execute, verify, commit. Use this for focused changes (a few files, clear scope) where the full /pipeline would be overkill.

When to use this vs. /pipeline: if the change needs requirements refinement (PM), architectural decisions (Principal), or touches multiple areas (backend + frontend + infra), use /pipeline instead.

Before Starting

Load context about the project and the change:

  1. Read docs/audit/00-project-context.md if it exists — lint command, test command, framework, conventions.
  2. Read docs/audit/01-architecture.md if it exists — component map and dependency graph.
  3. Read docs/audit/10-roadmap.md if it exists — the sequenced improvement plan.
  4. Read pipeline/context.md if it exists — open questions, prior decisions, fix log.
  5. If the project has a AGENTS.md, read the coding standards sections.
  6. If none of these exist, ask the user: "What are this project's lint/test commands, and are there coding conventions I should follow?"

Identify what to implement. The user may:

  • Name a specific item from the roadmap — look it up in docs/audit/10-roadmap.md
  • Describe the change directly — use their description as the spec
  • Say "next item" — pick the next unfinished item from the roadmap, respecting the sequence

If the scope is unclear, ask before planning.

Step 1: Plan

Write a detailed implementation plan before touching any code. The goal is to surface problems, missing context, and open questions before investing effort in coding.

The plan covers:

  1. Context — What's wrong today and the concrete impact. Why fix it now rather than later.

  2. Approach — The strategy. If there are multiple ways to do this, briefly note the alternatives and why this approach wins. Keep it to 2-3 sentences.

  3. File-by-file changes — Every file that needs modification, with the specific change described precisely enough for someone to review the plan without reading the code.

Read the full file on GitHub · 124 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 · 124 lines · 122 tokens per session scan A a76bad6486b2

Subscribe to this mod's changes

implement is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session and 1,603 once invoked, about $0.0006 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

semantix

Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.

Gnosil/semantix · 47 tokens

semantix-guide

Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…

Gnosil/semantix · 115 tokens

file-a-task

File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.

no-human-ai/no_human · 37 tokens

intuitive-tests

Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…

MiaoDX/intuitive-flow · 154 tokens

intuitive-flow

Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…

MiaoDX/intuitive-flow · 98 tokens

intuitive-preflight

Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…

MiaoDX/intuitive-flow · 112 tokens