agent-implementation

A workflow for carrying out an approved repository plan one task at a time, with commits and checks after each task. It uses a fresh worker for each implementation task and reviews the resulting changes.

In plain words
What is it for?
Implementing planned changes in a toolkit repository, checking modified files, reviewing diffs, creating focused commits, and running final verification.
Why use it?
It separates implementation into focused pieces and catches issues before the next task proceeds. It also provides clear stop conditions when work is blocked or unclear.

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/sflandergan/agentic-coding/agent-implementation
Any agent
npx skills add sflandergan/agentic-coding --skill agent-implementation
Clone the repo
git clone --depth 1 https://github.com/sflandergan/agentic-coding

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 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 $0.00021 $0.00484
Opus 5 $0.00010 $0.00242
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash 22773ba795f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-implementation 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.

.agents/skills/agent-implementation/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Implementation — Self-Maintenance

Controller orchestration for implementing plans against this toolkit repo.

Core principle: Fresh implement-task worker per task + verification gate = quality commits.

Continuous execution: Execute all tasks from the plan without routine pauses between tasks. Stop for: BLOCKED status, genuine ambiguity, or all tasks complete.

The Process

  1. Extract one task with enough context for isolated execution.
  2. Give the worker the full task text, relevant spec/plan paths, and current branch state.
  3. Review the worker report and diff before moving on.
  4. Fix and re-review every open issue before marking the task complete.
  5. Run final verification before any completion or push claim.

Worker Contract

The implement-task worker:

  • Implements exactly one task
  • Creates or modifies only the files specified
  • Runs task-level verification on changed files (shellcheck, bash -n, codespell on changed prose/markdown files)
  • Commits with a focused message
  • Reports status: DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, or BLOCKED
  • Does not push, create PRs, or dispatch other workers

Handling Worker Status

  • DONE: Verify the diff, move to next task.
  • DONE_WITH_CONCERNS: Read concerns. If about correctness, address before continuing.
  • NEEDS_CONTEXT: Provide missing context and re-dispatch.
  • BLOCKED: Assess: context problem → provide more; plan wrong → escalate to human.

Treat every worker escalation as actionable. If the worker said it's stuck, something needs to change.

Operating Rules

  • Start from a scoped branch.
  • Run the relevant verification before status claims and before moving to the next task.
  • Resolve correctness issues before continuing.
  • Dispatch workers sequentially by default; use parallel workers only for independent tasks touching disjoint files.
  • Give each worker the task text, relevant context, and branch state.

Completion

After all tasks complete and final verification passes:

Read the full file on GitHub · 58 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 · 58 lines · 21 tokens per session scan A 22773ba795f7

Subscribe to this mod's changes

agent-implementation is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 484 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens