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/pratiyush/llm-wiki/releasegit clone --depth 1 https://github.com/Pratiyush/llm-wikiWrote 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/commands/pratiyush/llm-wiki/release)<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/release"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/release.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 | $0.00000 | $0.00920 |
| Opus 5 | $0.00000 | $0.00460 |
| Sonnet 5 | $0.00000 | $0.00184 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
release 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk the llmwiki release process step by step.
Usage: /release # e.g. /release 0.9.0
This slash command loads docs/maintainers/RELEASE_PROCESS.md and
walks through every step interactively. The rule is: don't skip a
step even if it "should be" fine — skipping steps is how broken
releases ship.
Workflow
-
Load the release process doc —
docs/maintainers/RELEASE_PROCESS.mdhas the canonical checklist. Read it end to end before doing anything. -
Run the pre-flight — confirm all of:
- Master is green (
gh run list --branch master --limit 5) python3 -m pytest tests/ -qpasses on a clean checkoutpython3 -m llmwiki buildcompletes without new warnings- Preview the built site and click through every nav item
- No open
priority:criticalbugs (gh issue list --label priority:critical --state open)
If any of these fail, stop and fix them first.
- Master is green (
-
Bump the version — three files must agree:
llmwiki/__init__.py→__version__ = "<NEW>"pyproject.toml→version = "<NEW>"README.md→ version badge (Version-v<NEW>-7C3AED.svg) Runpython3 -m llmwiki --versionto confirm.
-
Update CHANGELOG — for every entry:
- Move from
## [Unreleased]into## [<NEW>] — YYYY-MM-DD - Group by
### Added/### Changed/### Fixed/### Removed - Add a one-line "Theme:" at the top of the new section
- Keep an empty
## [Unreleased]section above
- Move from
-
Spot-check PR numbers — every
#Nin the new section should link to a real merged PR. Rungh pr list --state merged --limit 30and cross-reference. -
Commit and tag — use these exact commands:
git add llmwiki/__init__.py pyproject.toml README.md CHANGELOG.md git commit -m "release(v<NEW>): bump version + CHANGELOG" git tag v<NEW> git push origin master v<NEW>Do NOT force-push master. Do NOT amend the release commit after tagging.
-
Create the GitHub Release:
gh release create v<NEW> --title "v<NEW>" --notes-from-tag --prereleaseThe
--prereleaseflag stays set for every0.x.yuntil1.0.0. -
Verify the Pages deploy:
gh run list --workflow=pages.yml --limit=3The new tag + the master push should both trigger the workflow. Watch both runs. Visit
https://pratiyush.github.io/llm-wiki/and confirm the new version badge is visible. -
Announce (optional) — post to X / LinkedIn if it's a milestone release (v0.5, v0.9, v1.0, ...).
-
Append to log — one line to
wiki/log.md:## [YYYY-MM-DD] release | v<NEW>
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 · 94 lines · 0 tokens per session scan A 2b70a7378c09
release is a command published in the GitHub repository Pratiyush/llm-wiki (383 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 920 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
sync-doctor
Detect MCP config drift and parse errors between Claude Code and target AI agents.
sync-validate
Validate Claude MCP schema and target capability compatibility before syncing.
sync-list
List all MCP servers configured in Claude Code with transport type and source.
/opsx-propose
Propose a new change - create it and generate all artifacts in one step.
note
Capture a short, time-bound note (task or reminder) under wiki/notes/. Auto-expires after 7 days. Usage: /note , /note task , /note reminder , /note list, /note done , /note clear.
/opsx-apply
Implement tasks from an OpenSpec change (Experimental).