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 commands/sprklai/zenii/update-docsgit clone --depth 1 https://github.com/sprklai/zeniiWhat 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 | $0.00000 | $0.01220 |
| Opus 5 | $0.00000 | $0.00610 |
| Sonnet 5 | $0.00000 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
update-docs 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Introspect Code & Update All Documentation Surfaces
This command reads the actual source code to count routes, tools, and providers, then updates every documentation surface (README, docs/, docs-site/, GitHub About) with the correct values.
It runs fully automatically with NO user prompts.
Instructions
Follow these steps strictly and sequentially. Do NOT ask the user for confirmation between steps — proceed automatically.
Step 1: Introspect source of truth
Count the actual values from code. Use Grep/Read tools — do NOT guess or use cached values.
1a. Count routes
Read no_commit/api-routes.md (canonical route list). Extract:
- Total from the
## Total:line at the bottom - Base routes count from the
## Base Routes (N)header - Feature-gated breakdowns from the
## Feature: name (N)headers
Do NOT re-parse routes.rs — the canonical file is the source of truth. If no_commit/api-routes.md does not exist, warn the user and skip route counting.
1b. Count tools
Read crates/zenii-core/src/boot.rs. Count:
- Base tools:
tool_registry.register(calls NOT inside#[cfg(featureblocks - Feature-gated tools:
tool_registry.register(calls inside#[cfg(featureblocks - Total: base + feature-gated
1c. Count providers
Read crates/zenii-core/src/ai/providers.json. Count entries in the providers array.
1d. Print summary
Print the introspected values:
Introspected values:
- Routes: {core} core + {channels} channels + {scheduler} scheduler + {workflows} workflows = {total} total
- Tools: {base} base + {feature_gated} feature-gated = {total} total
- Providers: {count} AI providers
Step 2: Find stale values
Search for stale/incorrect counts across all doc surfaces:
grep -rn "routes" README.md docs/ docs-site/ --include="*.md" | grep -E "\d+ (API )?routes"
grep -rn "built-in" README.md docs/ --include="*.md" | grep -E "\d+ built"
grep -rn "tools" README.md docs/ --include="*.md" | grep -E "\d+ (base |built-in )?tools"
grep -rn "providers" README.md docs/ --include="*.md" | grep -E "\d+ .* providers"
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 · 137 lines · 0 tokens per session scan A 2038a039bcc6
update-docs is a command published in the GitHub repository sprklai/zenii (23 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,220 tokens. 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 commands, from other repositories
onboard
Orient yourself in this repo — layout, entry points, and where the thing you are about to change lives.
code-apply-hermit
Hands the P1–P5 findings from the most recent /code-review to Hermit so Claude doesn't burn tokens re-reading every file and retyping every edit. Claude stays on judgment; Hermit does the mechanical apply.
collaborative-spec-builder-existing
Build an aspirational specification for existing code and identify gaps to address.
toefl-grade
TOEFL 답안/녹음 채점 — 로컬 LLM(Ollama)과 whisper.cpp로 4개 영역을 채점하여 SCORES.md에 점수를 누적 기록한다.
toefl-practice
TOEFL 유형 문제 생성 — 로컬 LLM(Ollama)이 reading/listening/speaking/writing 영역의 실전형 문제를 생성하여 practice/에 저장한다.
toefl-roadmap
이번 주 토플 학습 로드맵/과제 표시 — schedule.yaml에서 사용자가 지정한 학습 기간·요일·시간대·주차별 목표를 읽어 현재 날짜 기준으로 안내한다.