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.
npx agentmods add skills/sflandergan/agentic-coding/agent-implementationnpx skills add sflandergan/agentic-coding --skill agent-implementationgit clone --depth 1 https://github.com/sflandergan/agentic-codingWhat 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.
| Model | Per session | Once 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 |
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.
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
- Extract one task with enough context for isolated execution.
- Give the worker the full task text, relevant spec/plan paths, and current branch state.
- Review the worker report and diff before moving on.
- Fix and re-review every open issue before marking the task complete.
- 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:
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.
- yesterday First seen · 58 lines · 21 tokens per session scan A 22773ba795f7
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…