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/alanhuang168/ai-project-workflow/implnpx skills add AlanHuang168/AI-Project-Workflow --skill implgit clone --depth 1 https://github.com/AlanHuang168/AI-Project-WorkflowWrote 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/alanhuang168/ai-project-workflow/impl)<a href="https://agentmods.dev/skills/alanhuang168/ai-project-workflow/impl"><img src="https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/impl.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00699 |
| Opus 5 | $0.00000 | $0.00349 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
impl 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: impl description: Implement the project according to the approved PRD, architecture, detailed design, and test plan. Use when the user asks to begin implementation or invokes /impl. version: 1.0.0 stage: impl
Goal
Implement strictly according to the approved SDD and Test Plan, run suitable verification, and report real results.
Use Cases
- The user invokes
/impl. - The user asks to begin implementation.
- The user asks to implement according to the SDD.
Preconditions
docs/PRD.md,docs/ARCH.md,docs/SDD.md, anddocs/TEST.mdexist and are not empty.- Workflow state shows
sddcomplete unless the user explicitly approves a skip and the reason is recorded.
Required Context
AGENTS.md.ai-workflow/state.jsoncore/rules/execution-policy.mdcore/rules/verification-policy.mddocs/PRD.mddocs/ARCH.mddocs/SDD.mddocs/TEST.md- Relevant source and test directories
Inputs
- Approved SDD and Test Plan.
- Explicit implementation scope from the user.
Allowed Changes
- Business code and test code defined by the SDD.
- Necessary build, configuration, README, or script files.
.ai-workflow/state.json- Do not add business behavior that the SDD does not define.
Steps
- Confirm that upstream documents exist and are not empty.
- Extract tasks, interfaces, data structures, state transitions, error handling, and implementation order from the SDD.
- Extract acceptance criteria and verification commands from the Test Plan.
- Implement in small scoped steps according to the SDD.
- Stop and ask the user if the SDD does not cover a required business scenario.
- Run suitable build, test, or static checks after implementation.
- If verification fails, fix and rerun when possible. If not possible, report the failure and remaining risk.
- Write or update the implementation report when the project convention requires one.
- Update workflow state: add
impltocompletedStages, setcurrentStage = "review", and update the timestamp.
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.
- 4d ago First seen · 91 lines · 0 tokens per session scan A 65aa6e6e3e7e
impl is a skill published in the GitHub repository AlanHuang168/AI-Project-Workflow (27 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 699 tokens. 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 2026-08-30.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
Accessibility Manual Audit
Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.