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.
git clone --depth 1 https://github.com/briannaworkman/commonplaceWrote 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/briannaworkman/commonplace/lint)<a href="https://agentmods.dev/commands/briannaworkman/commonplace/lint"><img src="https://agentmods.dev/badge/commands/briannaworkman/commonplace/lint.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 5.1 | $0.00012 | $0.00595 |
| Opus 5 | $0.00006 | $0.00298 |
| Sonnet 5 | $0.00002 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
lint 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a maintenance pass over wiki/. Fix what is mechanical; report what needs a human.
1. Build the picture
Read every article. Collect every filename, every title:, and every [[wikilink]] target.
2. Broken links
A link whose text matches no filename. Usually one of two causes:
- The filename is wrong — it was slugified to
kebab-case. Rename the file to its exact title in Title Case with spaces. This is the common one. - The article doesn't exist — either fix the link text to point at the right article, or,
if the concept genuinely deserves its own article, write a short stub and add it to
wiki/INDEX.md.
Do not create a stub for every dangling link. A link to something that will never be an article — a person's name, a passing product mention — should stop being a link and become plain text.
3. Links split across lines
Search every article for a [[ whose closing ]] is on a later line. If the target (the
part before any |) contains the break, the link is dead — it resolves to nothing. Re-wrap
the line so the whole link sits together.
These are easy to miss because they are invisible in graph view whenever the same link also
appears in the article's related: list: the frontmatter copy resolves, so the connection
shows up and nothing looks faded. Fix them by reading, not by looking at the graph.
4. Orphans
Articles nothing links to. For each, find the most closely related article and link them — in both directions. If an article has outbound links but no inbound ones, the fix is usually to make one of its existing outbound links bidirectional rather than to invent a new relationship.
Prefer linking from a specific article over a broad hub. Wiring everything to the biggest hub makes that hub meaningless.
5. Near-duplicates
Two articles covering the same concept. Merge into the one with the better title: combine
their sources:, repoint every link, delete the loser, update wiki/INDEX.md.
6. Index and provenance
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.
- 7d ago First seen · 65 lines · 12 tokens per session scan A 3b4f46716576
lint is a command published in the GitHub repository briannaworkman/commonplace (5 stars, last pushed 27d ago), licensed MIT. It adds 12 tokens to every session and 595 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 2026-08-31.
Other commands, from other repositories
okf
A command that exports a private knowledge wiki into an OKF-compatible bundle. OKF is a format for packaging knowledge, with a separate guarded mode for preparing material to share externally.
query
A read-only command for answering questions from a project wiki, using an index and a stored record of supported claims. It checks that the wiki sources and claim records are valid before answering.
curate
A command for maintaining a file-based knowledge wiki. It can review pages, shorten overlong material, manage page lifecycles, find possible contradictions, and rebuild weak connections between notes.
doctor
A diagnostic command for checking and, when requested, repairing an llm-brain installation. It also offers read-only profiles for demo, private use, or preparing a shareable setup.
ingest
A command for adding information to a file-based knowledge wiki from web pages, files, or text notes. It classifies the material, updates or creates wiki pages, and adds links between related pages.
express
A command that gathers related wiki pages and drafts content from them. It supports blog posts, lecture slides, weekly or monthly summaries, and in-depth reports.