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/hiepdnh/agentic-development-lifecycle/pm-maintainnpx skills add hiepdnh/Agentic-Development-Lifecycle --skill pm-maintaingit clone --depth 1 https://github.com/hiepdnh/Agentic-Development-LifecycleWrote 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/hiepdnh/agentic-development-lifecycle/pm-maintain)<a href="https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/pm-maintain"><img src="https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/pm-maintain.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 5.1 | $0.00083 | $0.01294 |
| Opus 5 | $0.00042 | $0.00647 |
| Sonnet 5 | $0.00017 | $0.00259 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
pm-maintain 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 6d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: /pm-maintain
Role: PM / Dev / BE
Mục đích: Workflow tối giản cho giai đoạn maintenance — đủ control mà không overhead như active sprint.
Context
Maintenance phase khác active development:
- Không có sprint planning / backlog grooming thường xuyên
- Requests đến theo kiểu "ad-hoc" — khách JP email bug report bất kỳ lúc
- Team nhỏ hơn — thường 1-2 dev + 1 BE part-time
- JP outsource: SLA / 保守契約 quy định response time và fix time
- Cần track history rõ để billing / báo cáo tháng cho khách
Maintenance Workflow
JP Bug Report / Request
→ Triage (classify + priority)
→ Fix (tiny: patch trực tiếp / normal: dev-analyze → implement)
→ QA verify
→ Release (hotfix hoặc monthly batch)
→ 月次報告書 (monthly report gửi JP)
Hướng dẫn thực hiện
Bước 1 — Gate: Xác định loại yêu cầu
Dùng AskUserQuestion tool:
- Loại: Bug fix / Minor improvement / Performance issue / Security patch / Question từ JP
- Source: Khách JP báo / User báo / Monitoring alert / Internal discovery
- SLA: Có SLA obligation không? Response time yêu cầu?
Chờ confirm.
Bước 2 — Triage
Classify theo Maintenance Priority Matrix:
## Triage: [Tên vấn đề]
**Priority**: P1 / P2 / P3 / P4
| Priority | Định nghĩa | Target fix time |
|----------|-----------|----------------|
| P1 — Critical | Production down / Data loss / Security breach | Fix ngay, trong ngày |
| P2 — High | Feature broken, workaround khó | Fix trong 1-3 ngày |
| P3 — Medium | Feature broken, có workaround | Fix trong 1-2 tuần |
| P4 — Low | UI glitch / minor inconvenience | Batch vào monthly release |
**Classification**: [P1/P2/P3/P4]
**Lý do**: [...]
**Assignee**: [Dev name]
**Fix deadline (JST)**: [Date]
Bước 3 — Fix workflow theo priority
P1 — Critical (Hotfix)
P1 Hotfix Protocol:
1. Thông báo BE ngay → BE notify khách JP trong 30 phút
2. Dev fix (dùng tiny lane — patch trực tiếp)
3. QA quick verify (smoke test)
4. Deploy hotfix ngay
5. Post-mortem: ghi vào docs/reports/incident-[date].md
6. Gửi 障害報告書 cho khách JP (dùng /ops-incident)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 145 lines · 83 tokens per session scan A e6698260d5cf
pm-maintain is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 9d ago), licensed MIT. It adds 83 tokens to every session and 1,294 once invoked, about $0.0004 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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-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…