agentmods.dev

llm-wiki: Command for Claude Code

.claude/commands/wiki-candidates.md

wiki-candidates is a command for Claude Code from Pratiyush/llm-wiki. It costs 0 tokens per session (475 once invoked), scanned A, original, MIT.

A command guide for reviewing proposed wiki pages that have not yet been accepted into the trusted wiki.

In plain words
What is it for?
Use it to triage pages under the wiki's candidate area and promote valid pages, combine duplicates, or archive false entries.
Why use it?
It defines how to list, approve, merge, or discard candidate pages while keeping an audit trail.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Pratiyush/llm-wiki's own configuration. It tells Claude Code how to work on llm-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki configures →

Part of the llm-wiki plugin — 6 skills, 18 commands shipped together

not rated 387repo +3 2mo ago A scan 0 tokens original MIT
View source ↗ Pratiyush/llm-wiki
Reuse

Borrowing it

Nothing to install: this file belongs to Pratiyush/llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Pratiyush/llm-wiki/master/.claude/commands/wiki-candidates.md
Clone the repo
git clone --depth 1 https://github.com/Pratiyush/llm-wiki

Made for: Claude Code.

Or install llm-wiki, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

Wrote 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.

agentmods badge for wiki-candidates

README.md
[![agentmods](https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-candidates/github.svg)](https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-candidates)
Your own site
<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-candidates"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-candidates/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.

agentmods 80×15 button for wiki-candidates

Your own site · 80×15
<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-candidates"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-candidates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00475
Opus 5 $0.00000 $0.00237
Sonnet 5 $0.00000 $0.00095
Haiku 4.5 $0.00000 $0.00047

Measured 10d ago against content hash 42c5fc3847d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiki-candidates 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 10d 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.

.claude/commands/wiki-candidates.md · 57 lines

What it actually says

Review and triage candidate wiki pages — promote, merge, or discard.

Candidate pages live under wiki/candidates/<kind>/<slug>.md and were created by /wiki-ingest for new entities/concepts the LLM detected. They are not part of the trusted wiki layer until a human approves them.

Usage: /wiki-review

Workflow

  1. List all pending candidates:

    python3 -m llmwiki candidates list

    Or filter to stale (age > 30 days):

    python3 -m llmwiki candidates list --stale

  2. For each candidate, decide:

    • promote — candidate is legitimate and not a duplicate. Moves it into the trusted tree (wiki/entities/ or wiki/concepts/) and rewrites status: candidate → status: reviewed.

      python3 -m llmwiki candidates promote --slug MyEntity

    • merge — candidate is essentially a duplicate of an existing page. Appends the candidate's body under a ## Candidate merge — <date> heading in the target page, then archives the candidate.

      python3 -m llmwiki candidates merge --slug DuplicateFoo --into Foo

    • discard — candidate is a hallucination or noise. Moves it to wiki/archive/candidates/<timestamp>/ with a .reason.txt audit-trail file.

      python3 -m llmwiki candidates discard --slug BogusEntity \
  --reason "not a real company; LLM hallucinated"

  3. After any promote/merge, run /wiki-lint to catch broken wikilinks from pages that used to point at the candidate location.

  4. Append to wiki/log.md:

    ## [YYYY-MM-DD] review | <N> promoted, <M> merged, <K> discarded
  • #51 — the issue that added this workflow
  • /wiki-lint — finds stale candidates (age > 30 days) automatically
  • /wiki-ingest — routes new pages to candidates/ instead of direct
Changes

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.

  1. 10d ago First seen · 57 lines · 0 tokens per session scan A 42c5fc3847d0

Subscribe to this mod's changes

wiki-candidates is a command published in the GitHub repository Pratiyush/llm-wiki (387 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 475 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.

Claude CodePlanningWriting and docsaicodex-clicursordeveloper-toolskarpathy
Related

Other commands, from other repositories

prompt-pilot

Rewrite a rough prompt into a precise, context-enriched prompt (read-only — never implements the task).

savasturkoglu1/promptpilot-plugin · 21 tokens

sdd-apply

Implement SDD tasks — writes code following specs and design.

Gentleman-Programming/gentle-ai · 11 tokens

sdd-init

Initialize SDD context — detects project stack and bootstraps persistence backend.

Gentleman-Programming/gentle-ai · 14 tokens

kb-ingest

Ingest external material into Sources/ inside the bound project KB, then update registry, index, and daily note as needed.

Galaxy-Dawn/claude-scholar · 29 tokens

ijfw-audit

Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].

FerroxLabs/ijfw · 28 tokens

modernization-flow-grouping

Phase 4 Class Grouping of modernization-flow.

griddynamics/rosetta · 15 tokens