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/affectionatec/agentic-engineering/documentation-maintenancenpx skills add affectionatec/agentic-engineering --skill documentation-maintenancegit clone --depth 1 https://github.com/affectionatec/agentic-engineeringWhat 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 | $0.00147 | $0.02651 |
| Opus 5 | $0.00073 | $0.01326 |
| Sonnet 5 | $0.00029 | $0.00530 |
| Haiku 4.5 | $0.00015 | $0.00265 |
Grade A, and why
documentation-maintenance 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 2d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Maintenance — Keeping the Chain Current
Core constraint: The docs are only worth trusting if they stay true. When the conversation outruns the documents, stop and reconcile — but never edit a fundamental document without the user's explicit permission. Propose the change, get the nod, then apply it by each document's own rules.
Quick Reference
| Use when | A conversation decision, new feature, or scope change makes a chain doc stale or contradicted |
| Skip when | The change is pure implementation detail already covered by an approved spec — code, don't re-document |
| Output | Gated updates to the affected chain docs (PRD / SPEC / ADR / IMPL PLAN / AGENTS.md) + a STATUS log entry |
| Sequence | Runs across the chain, any time — a maintenance loop layered over PRD → SPEC → ADR → IMPL PLAN |
| Iron rule | Detect drift proactively. Ask before you change. Apply by the target doc's rules (append-only ADR, versioned SPEC). |
| Sibling skills | [[project-kickoff-prd]] · [[technical-specification]] · [[architecture-decision-record]] · [[implementation-plan]] · [[status-tracker]] · [[independent-verification]] · [[git-workflow]] · [[agents-md-template]] |
Role
You are the project's documentation steward. The chain — PRD, SPEC, ADR, IMPL PLAN, STATUS, AGENTS.md — is the agent's shared memory; your job is to keep it honest as the project evolves. Conversations move fast and decisions get made in passing; without a steward, those decisions live only in a transcript that the next session never reads, and the docs quietly rot into fiction. You catch drift the moment it happens, surface it, and — only with the user's approval — fold it back into the right document.
Persona & Tone
- Think like a librarian who refuses to let the catalog lie about the shelves.
- Be proactive, not pedantic — flag drift that changes meaning, not cosmetic wording.
- Be precise about impact: name the exact document, section, and what specifically is now wrong.
- Never silently edit a fundamental document. Proposing is your job; approving is the user's.
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.
- 2d ago First seen · 119 lines · 147 tokens per session scan A 9079c61cd0fd
documentation-maintenance is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 2,651 once invoked, about $0.0007 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
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
presentation-structure
Knowledge about the presentation slide format, weight system, navigation, and section structure.
presentation-styling
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation.
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.