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/daniyalahmed21/skillforge/wiki-syncnpx skills add daniyalahmed21/skillforge --skill wiki-syncgit clone --depth 1 https://github.com/daniyalahmed21/skillforgeWrote 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/daniyalahmed21/skillforge/wiki-sync)<a href="https://agentmods.dev/skills/daniyalahmed21/skillforge/wiki-sync"><img src="https://agentmods.dev/badge/skills/daniyalahmed21/skillforge/wiki-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 | $0.00043 | $0.01412 |
| Opus 5 | $0.00022 | $0.00706 |
| Sonnet 5 | $0.00009 | $0.00282 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
wiki-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 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Sync
Maintain the repository's documentation so it stays current with the codebase. Work inside the
repo's existing docs/ tree - a single flat folder. Never create a nested docs/wiki/ folder
(a second doc tree competing with docs/ causes drift). docs/README.md is the single index +
code map; the topic docs live beside it.
Every repo this skill touches should end up with the SAME shape (the spine below), so a human or a coding agent always knows where to look. Consistency across repos is a primary goal.
Structure
Flat docs/ only. Lowercase, kebab-case filenames. Two layers:
The spine (always present)
docs/README.md- the entry point. Must contain, in order:- One-line statement of what the project is + the stack.
- A links section listing every topic page with a one-line description.
- A "Code map - where things live" table (precise dir/file -> responsibility).
- A key environment variables table (names + purpose only; never values or secrets).
docs/.wiki-state.json- incremental-sync state (see State).
Canonical topic pages (create ONLY when that subsystem actually exists)
Use these standard filenames so repos stay uniform. Do NOT create a page for a subsystem the repo does not have - an empty stub is worse than an absent page.
architecture.md- components, request/data flow, module boundaries, key decisions.data-model.md- entities/tables/migrations/schema ownership (repos with a datastore).integrations.md- upstream/downstream services, external APIs, message queues/events, auth.development.md- local setup, running, scripts, testing, and gotchas.
Anything more specific is a domain page: one concept per page, kebab-case, descriptive name
(e.g. frontend-graphql-data-layer.md, contract-signing-flow.md). Prefer fewer, larger pages over
many stubs.
Page template (every page follows it)
# Titleand a one-line purpose sentence.- An "At a glance" bullet summary (3-6 bullets).
- Body sections. Every non-trivial claim cites a real path, ideally
file:line. - A "where things live" table where it aids navigation.
- A short "verified against source" note (commit sha or date). Never invent behavior; if something is unverified, say so.
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 · 114 lines · 43 tokens per session scan A 7751a3ee62da
wiki-sync is a skill published in the GitHub repository daniyalahmed21/skillforge (6 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,412 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.
Other skills, from other repositories
system-design
Production system design — scalability patterns, trade-off analysis, database selection, caching strategy, API design, and architecture decisions.
system-design-interview
Apply system design principles from System Design Interview by Alex Xu. Covers scaling (load balancing, DB replication, sharding, caching, CDN), estimation (QPS, storage, bandwidth), the 4-step framework, and 12 real designs: rate limiter, consistent hashing, key-value store, unique ID generator, URL shortener, web…
design-expert
Expert-level system design, architecture patterns, scalability, and distributed systems.
architecture-paradigm-cqrs-es
Applies CQRS and Event Sourcing for read/write separation and audit trails. Use when designing systems with complex domain logic or full state-change history.
architecture-paradigm-microservices
Applies microservices for independent deployment and per-service scaling. Use when teams need autonomous release cycles with distinct capability scaling needs.
docker-local-build
Build and test Kurtosis from source on local Docker. Compiles all components (engine, core, files-artifacts-expander), builds Docker images, installs the CLI, and restarts the engine. Use when developing Kurtosis and testing changes locally with Docker.