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/mengrru/spherse/doc-syncnpx skills add mengrru/Spherse --skill doc-syncgit clone --depth 1 https://github.com/mengrru/SpherseWrote 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/mengrru/spherse/doc-sync)<a href="https://agentmods.dev/skills/mengrru/spherse/doc-sync"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/doc-sync.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 | $0.00037 | $0.01099 |
| Opus 5 | $0.00018 | $0.00549 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
doc-sync 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Sync Skill
Purpose
Every code change has a documentation surface. This skill walks the full checklist so nothing is missed: official docs stay current, package READMEs stay accurate, and the backlog reflects completed work. Run it when a feature/infra/bugfix is finished, or whenever the user asks to commit.
Process
-
Determine the change surface.
- If changes are uncommitted: read
git statusandgit diff(staged + unstaged). - If the work spans commits: read
git logand per-commit diffs for this branch. - List the touched packages, directories, public exports, data formats, and cross-package seams.
- If changes are uncommitted: read
-
Walk the sync checklist below and check every row that matches the change surface. Do not skip rows silently — each row must end up either "updated" or "no impact, because ...".
-
Apply updates following the writing rules.
-
Report: list each checklist row with its outcome (updated / no impact). Flag anything you intentionally did not update and why.
Sync checklist
| Change | Must sync |
|---|---|
| Files/dirs/packages added, moved, or removed | docs/official/project-structure.md (tree + surrounding notes). Exception: .agents/ and .opencode/ are deliberately NOT recorded there — do not add them back |
| Architecture decisions, package boundaries, capability/assembly changes, API contract approach | the matching domain file under docs/official/architecture/ (routing table in docs/official/README.md; follow its writing rules) |
| An architecture decision made or overturned | append a new ADR under docs/dev/decisions/ (thin: 10-20 lines; overturned ⇒ only flip status to superseded); link it from the matching official doc claim |
| Data file formats, storage location conventions | docs/official/data-conventions.md |
| New domain concept or overloaded term introduced | docs/official/glossary.md (one-line definition + authoritative doc link) |
| Package-level coding/review rules | the package's own README (packages/{pkg}/README.md) |
| User-visible strings | the i18n skill (add keys + translations) |
| Design system, theme mechanism, chat DOM/layout/CSS tokens, themeable selectors | packages/presets/skills/spherse-create-ui-theme/ and packages/presets/skills/spherse-create-agent-chat-theme/ |
Presets templates or skill sources edited under packages/presets/ |
trigger the sync build so generated constants are usable: npm run build --workspace=packages/presets (see packages/presets/README.md) |
| A backlog item completed | delete its entry in docs/dev/backlog.md (no tick-and-keep); append newly-discovered follow-ups as new items following the entry norms in that file's header |
| User gave a design/code convention correction that was agreed and executed during this session | distill it via first-principles analysis and persist it to the correct layer (root AGENTS.md rules / package README / official domain file / skill) — merge into an existing entry when possible; one-off factual fixes do not qualify (see AGENTS.md「规范演进」) |
| New tooling, commands, or verification steps | the relevant section of AGENTS.md (keep it lean — links, not detail) |
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.
- 5d ago First seen · 56 lines · 37 tokens per session scan A c532c6eba6d5
doc-sync is a skill published in the GitHub repository mengrru/Spherse (63 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,099 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 2026-08-30.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.
security-review
How to review PRs for security — credentials, injection, workflow permissions, supply chain, git operation safety.