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 Nano-Nimbus/locus --skill locus-auditgit clone --depth 1 https://github.com/Nano-Nimbus/locusWrote 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/nano-nimbus/locus/locus-audit)<a href="https://agentmods.dev/skills/nano-nimbus/locus/locus-audit"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-audit/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/nano-nimbus/locus/locus-audit"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-audit.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 | $0.00077 | $0.00702 |
| Opus 5.5 | $0.00031 | $0.00281 |
| Sonnet 5.5 | $0.00015 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
locus-audit 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locus Audit (Experimental)
Experimental. Results are advisory only.
Run a health audit on a Locus memory palace. Evaluates room sizes, session
log accumulation, retrieval depth, and feedback rates. Produces a prioritised
list of recommended actions and writes reports to _metrics/.
Usage: /locus-audit [room-path]
Arguments:
room-path(optional) — scope to a single room (e.g.projects/api-platform). Omit to audit the entire palace.
When to run
Run /locus-audit when:
- Any room has accumulated 5+ session logs
- A recent run had unexpectedly high retrieval depth
/locus-feedback failhas been used more than once recently- You haven't run an audit in more than 30 days
The locus skill will suggest running an audit when trigger conditions are met (see the audit algorithm at https://github.com/Nano-Nimbus/locus/blob/main/spec/audit-algorithm.md).
Steps
1. Identify palace root
Walk up from cwd looking for INDEX.md. If not found, report an error.
2. Run the audit
The size-limit half of the audit is also available without the CLI:
locus lint --root <palace_root> reports every locus.size-limit violation in
the palace. It does not score retrieval depth or feedback, so it complements the
audit rather than replacing it.
Use the locus-audit CLI if available:
locus-audit --palace <palace_root> [--room <room-path>]
If the CLI is not installed, perform the audit manually:
- Discover rooms (dirs with a matching
<dir-name>.mdmain file) - Collect signals per room (line counts, session log count, mtime of oldest log)
- Load
_metrics/*.jsonfor retrieval and feedback signals - Score each room per the audit algorithm linked above
- Build the action items list
3. Report
Print the full markdown health report. Highlight:
- Any
criticalrooms at the top - The prioritised action items list
- The summary table
4. Write reports
Write _metrics/audit-<timestamp>.md and _metrics/audit-<timestamp>.json.
Update _metrics/_last-audit.txt with the current timestamp.
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.
- 1mo ago Changed · +16 lines · +77 tokens per session cd5e60d38e2d
- 1mo ago First seen · 79 lines · 0 tokens per session scan A c328293982f7
locus-audit is a skill published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 702 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…