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 skills add bobbyjohnstx/tinycode --skill wikigit clone --depth 1 https://github.com/bobbyjohnstx/tinycodeWrote 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/bobbyjohnstx/tinycode/wiki)<a href="https://agentmods.dev/skills/bobbyjohnstx/tinycode/wiki"><img src="https://agentmods.dev/badge/skills/bobbyjohnstx/tinycode/wiki/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bobbyjohnstx/tinycode/wiki"><img src="https://agentmods.dev/badge/skills/bobbyjohnstx/tinycode/wiki.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00014 | $0.00776 |
| Opus 5 | $0.00007 | $0.00388 |
| Sonnet 5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
wiki 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 8d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki
Use this skill when you need to store, retrieve, or manage project-level knowledge that should persist across sessions and be discoverable by future agents.
When to Use
Use this skill when:
- You discover project-specific patterns, conventions, or gotchas worth preserving
- A debugging session uncovers a root cause or workaround that others will hit again
- An architectural decision is made with rationale that should be recorded
- Environment setup quirks or platform-specific issues are identified
- You want to check if existing wiki knowledge is relevant before starting a task
- Onboarding context needs to be captured for future contributors
When Not to Use
- Scratch notes for the current session only — use the notepad instead
- User preferences or directives — use project memory (
omt_project_memory_*) - Direct edits to
CLAUDE.mdorAGENTS.md— edit those files directly - Session-only working state — keep it in the conversation or notepad working memory
- Ephemeral task progress — use notepad working memory or state tools
Available Tools
omt_wiki_query— search across all wiki pages by keywords, tags, or categoryomt_wiki_read— read a specific wiki page by filename or slugomt_wiki_list— list all wiki pages with summariesomt_wiki_add— create a single new wiki page directlyomt_wiki_ingest— create or merge knowledge into wiki pages (handles existing page merging)omt_wiki_delete— remove a wiki page by filename
Workflow
- Query first — before starting a task, query the wiki for existing knowledge that might be relevant. Use
omt_wiki_querywith keywords from the task description. This avoids re-discovering known issues or contradicting established decisions. - Use findings — incorporate wiki knowledge into your work. Reference existing decisions, avoid known pitfalls, and follow documented patterns.
- Ingest durable findings — after completing work, ingest any durable findings back into the wiki. Ask yourself: would a future agent benefit from knowing this? If yes, write it to the wiki.
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.
- 8d ago First seen · 64 lines · 14 tokens per session scan A 5cba7e7588a5
wiki is a skill published in the GitHub repository bobbyjohnstx/tinycode (12 stars, last pushed 8d ago), licensed MIT. It adds 14 tokens to every session and 776 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
gini-bug-report
File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.
github-issues
Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.
omd-tickets
A tool for viewing the currently actionable tickets in a project map and bringing back results from background research jobs. A ticket is a tracked piece of work, while a project map shows how those pieces depend on one another.