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/wefio/nodememorygraph/doc-maintenancenpx skills add wefio/NodeMemoryGraph --skill doc-maintenancegit clone --depth 1 https://github.com/wefio/NodeMemoryGraphWrote 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/wefio/nodememorygraph/doc-maintenance)<a href="https://agentmods.dev/skills/wefio/nodememorygraph/doc-maintenance"><img src="https://agentmods.dev/badge/skills/wefio/nodememorygraph/doc-maintenance.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 | $0.00060 | $0.00879 |
| Opus 5 | $0.00030 | $0.00439 |
| Sonnet 5 | $0.00012 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
doc-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 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation maintenance
Keep NMG documentation useful as an interface between users, Agents, design, and implementation. Read the documentation index before editing. Use its Chinese counterpart when Chinese wording is part of the task.
Workflow
- Classify the change before writing. Decide whether it changes normative behavior, records rationale, reports evidence, changes completion status, adds unresolved work, or changes user instructions.
- Find the existing owner. Search titles and relevant terms. Update the owning document instead of creating another summary. Git preserves editing history. If a detail remains only in Git and would be expensive to rediscover, leave a commit or decision link in the relevant audit or decision document.
- Update the right surface.
- Behavior and architecture:
docs/design/design.mdand, when useful, one owning topic design. - Rationale and alternatives: a record under
docs/decisions/. - Measured results:
docs/experiments/; never promote a result into a design claim without an explicit decision. - Current implementation evidence:
docs/design/completion-audit.md. - Unresolved action only:
docs/design/temporary-todo.md; remove it when done. - User or Agent operation: README, Skill, or operating guide that owns it.
- Behavior and architecture:
- Handle supersession explicitly. Refine an existing owner when possible. Cross-link old and new decisions; archive a fully superseded decision, or state the remaining scope when supersession is partial.
- Maintain useful bilingual coverage. Root and docs indexes stay paired. New or materially changed decisions should normally be paired. Preserve the same decision, warnings, and commands, but do not force paragraph-for-paragraph equivalence. Experiments and internal notes may remain single-language.
- Keep status honest. Separate implemented, validated, enabled, default, deferred, and out-of-scope states. A passing controlled test is not natural product evidence; an experiment result is not a default-policy decision.
- Verify. Apply the CI contract, then run
npm run docs:checkand the code or evaluation checks needed by the underlying change. Review warnings rather than hiding them. If automation policy must change, update the contract first and the verifier second.
What ships with it
1 file 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.
- 4d ago First seen · 70 lines · 60 tokens per session scan A 9eb9c059d3d2
doc-maintenance is a skill published in the GitHub repository wefio/NodeMemoryGraph (0 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 879 once invoked, about $0.0003 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
skills-constitution
当 Agent 接到专业任务（编码/爬虫/文件操作/API调用/数据分析/文档/部署/推送等）时，强制先查记忆层和技能索引，有匹配必用、无匹配必搜、答复时自动推荐（排除已装）。用于防止 Agent 跳过技能直接硬扛通用能力。跨平台通用（WorkBuddy/Claude/ChatGPT/Cursor/Gemini 等 20+ 框架）。完整版本史见 CHANGELOG.md。.
add-memory-system
Research and integrate a new agent-memory repository into Agent Memory Atlas. Use when asked to add, analyze, catalog, or compare a memory system in this repository, including its commit-pinned system report, comparative overview coverage, homepage card, generated site, and validation.
reanalyze-memory-system
Re-read a repository Agent Memory Atlas already has a report for, at a newer commit, and fold what changed into the existing report. Use when asked to re-analyze, re-read, re-pin, refresh, or check for updates on a system already in the atlas, when an upstream project reports a fix, or when a freshness check flags a…
remove-meta-narrative
Detect and remove narration of the project's own history from published pages, so a reader gets the current state instead of a draft's changelog. Use before publishing or committing any edit to content/ or site/, when correcting a claim that turned out wrong, when folding a new finding into an existing page, and…
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.