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 skills add thangchung/agent-engineering-experiment --skill create-implementation-plangit clone --depth 1 https://github.com/thangchung/agent-engineering-experimentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thangchung/agent-engineering-experiment/create-implementation-plan)<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/create-implementation-plan"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/create-implementation-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/create-implementation-plan"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/create-implementation-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.02021 |
| Opus 5.5 | $0.00012 | $0.00808 |
| Sonnet 5.5 | $0.00006 | $0.00404 |
| Haiku 4.5 | $0.00003 | $0.00202 |
Grade A, and why
create-implementation-plan 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 1mo 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.
This is a copy
84% identical to create-implementation-plan — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Implementation Plan
Primary Directive
Your goal is to create a new implementation plan file for ${input:PlanPurpose}. Your output must be machine-readable, deterministic, and structured for autonomous execution by other AI systems or humans.
Execution Context
This prompt is designed for AI-to-AI communication and automated processing. All instructions must be interpreted literally and executed systematically without human interpretation or clarification.
Core Requirements
- Generate implementation plans that are fully executable by AI agents or humans
- Use deterministic language with zero ambiguity
- Structure all content for automated parsing and execution
- Ensure complete self-containment with no external dependencies for understanding
Plan Structure Requirements
Plans must consist of discrete, atomic phases containing executable tasks. Each phase must be independently processable by AI agents or humans without cross-phase dependencies unless explicitly declared.
Phase Architecture
- Each phase must have measurable completion criteria
- Tasks within phases must be executable in parallel unless dependencies are specified
- All task descriptions must include specific file paths, function names, and exact implementation details
- No task should require human interpretation or decision-making
AI-Optimized Implementation Standards
- Use explicit, unambiguous language with zero interpretation required
- Structure all content as machine-parseable formats (tables, lists, structured data)
- Include specific file paths, line numbers, and exact code references where applicable
- Define all variables, constants, and configuration values explicitly
- Provide complete context within each task description
- Use standardized prefixes for all identifiers (REQ-, TASK-, etc.)
- Include validation criteria that can be automatically verified
Output File Specifications
- Save implementation plan files in
/plan/directory - Use naming convention:
[purpose]-[component]-[version].md - Purpose prefixes:
upgrade|refactor|feature|data|infrastructure|process|architecture|design - Example:
upgrade-system-command-4.md,feature-auth-module-1.md - File must be valid Markdown with proper front matter structure
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.
- 1mo ago First seen · 185 lines · 29 tokens per session scan A 5501088e57ff
create-implementation-plan is a skill published in the GitHub repository thangchung/agent-engineering-experiment (27 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 2,021 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 84% identical to create-implementation-plan, differing in 29 lines, and is treated as a copy.
Other skills, from other repositories
phoenix-cli-development
Design and implementation guide for the Phoenix CLI (px). Covers the noun-verb command structure, dual-audience design (humans and coding agents), Commander.js patterns, configuration resolution, output formats, exit codes, and conventions for adding or modifying commands. Triggers when working on phoenix-cli commands…
playground
Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground ui. operation call, including single-shot prompt rewrites.
phoenix-graphql
Write efficient GraphQL queries against the Phoenix API. Load this skill in two cases: (1) before composing any non-trivial GraphQL query yourself for data analysis (via the phoenix-gql bash command) — it contains schema entrypoints and patterns that eliminate the need for introspection; (2) when the user asks for…
datasets
Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a dataset is in view or the user asks what a dataset is, how splits work, what an output "means", or how datasets relate to experiments and evals. This skill governs…
evaluators
Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve an existing one's logic or rubric, choose labels, or decide what to measure on a dataset or experiment. Do NOT trigger on: (1) manual prompt drafting (use…
experiments
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a dataset with experiments, compare experiment runs, read experiment quality/latency/cost, or decide whether a change actually helped. Running a prompt over a dataset…