aiops-implement

aiops-implement is a skill for Claude Code, Codex from yugasun/aiops. It costs 30 tokens per session (770 once invoked), scanned A, original, Apache-2.0.

A delivery workflow for implementing a feature from a product brief, issue description, or technical specification. It coordinates coding, tests, code review, and simplification checks through ordered approval gates.

In plain words
What is it for?
Use it to implement planned work, write tests for public interfaces, run review and pruning steps, and continue only when each required gate is satisfied. It commits only after user approval.
Why use it?
It makes the implementation process explicit and prevents later stages from starting before earlier checks pass. It also records the current delivery stage and can assess which parts of the code may be affected by a change.

Skill for Claude CodeCodex

Part of the aiops plugin — 23 skills, 9 agents shipped together

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

Made for: Claude Code, Codex.

Or install aiops, the plugin that ships this one along with the rest of its 23 skills, 9 agents.

Wrote 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.

agentmods badge for aiops-implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/yugasun/aiops/aiops-implement.svg)](https://agentmods.dev/skills/yugasun/aiops/aiops-implement)
Your own site
<a href="https://agentmods.dev/skills/yugasun/aiops/aiops-implement"><img src="https://agentmods.dev/badge/skills/yugasun/aiops/aiops-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 770 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 $0.00030 $0.00770
Opus 5 $0.00015 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 4d ago against content hash 9e99a34eebd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aiops-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 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.

skills/aiops-implement/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aiops-implement

Implement from PRD, issue brief, or tech-spec. Not for grill/alignment — lean active only while writing code.

Invoked by Flow Conductor delivery phase (builder agent). Update flow.state.yamldelivery_sub_phase as you progress.

Preconditions

  • Issue brief or issues/<current> AC, or tech-spec.md + NOTES.md
  • DESIGN_REVIEW.md APPROVE when design review ran in this flow
  • If /prototype ran: VERDICT.md before absorbing prototype learnings

Impact analysis (before implement)

If graphify-out/graph.json exists, tell the user "查询代码图谱评估修改影响面" then query /code-graph query impact <target-file> before writing code to understand the blast radius. Log affected modules in the journey context so the builder knows what might break.

Orchestration (hard gates — fixed order)

Run sub-phases in order. Do not skip unless user explicitly exempts a step (e.g. mechanical fix → skip new tests).

Sub-phase delivery_sub_phase Who Skill / action Gate to advance
1 implement builder lean ladder + write code Tests for changed behaviour pass
2 implement builder /tdd at public interfaces Red-green on agreed surface
3 prune quality-auditor /prune on diff Findings listed or "Lean already"
4 review code-reviewer /review vs NOTES/tech-spec/issue REVIEW.md APPROVE
5 ready_for_commit Set journey gate ready_for_commit User may ask gitops to ship

Record in journey gates_satisfied: prune_done, review_approve, ready_for_commit.

File size

If any file you touch approaches 500 lines, invoke /file-refactor before advancing to prune — split per that skill (types → utils → hooks → sub-components). Skip only when the user exempts or the file is intentionally monolithic.

Wave-based execution (when tasks.md has frontmatter)

When .scratch/<slug>/tasks.md contains YAML frontmatter with waves:, execute tasks wave by wave:

Read the full file on GitHub · 63 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. 4d ago First seen · 63 lines · 30 tokens per session scan A 9e99a34eebd0

Subscribe to this mod's changes

aiops-implement is a skill published in the GitHub repository yugasun/aiops (4 stars, last pushed 15d ago), licensed Apache-2.0. It adds 30 tokens to every session and 770 once invoked, about $0.0002 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.