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-consolidategit 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-consolidate)<a href="https://agentmods.dev/skills/nano-nimbus/locus/locus-consolidate"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-consolidate/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-consolidate"><img src="https://agentmods.dev/badge/skills/nano-nimbus/locus/locus-consolidate.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 | $0.00089 | $0.01337 |
| Opus 5 | $0.00044 | $0.00668 |
| Sonnet 5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
locus-consolidate 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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locus Consolidate
Merges accumulated session logs into canonical room files, enforces size limits, and archives processed logs. Run per room — if multiple rooms need consolidation, run this skill once per room.
Arguments: $ARGUMENTS — room path relative to palace root (e.g. projects/my-project).
If omitted, detect rooms needing consolidation automatically (Step 1b).
Step 1 — Identify the target room
1a — Argument provided:
Navigate to <palace-root>/$ARGUMENTS. Verify the directory exists and contains
a room main file and a sessions/ subdirectory.
1b — No argument (auto-detect):
Read INDEX.md to get all room paths. For each room, check:
- Does
sessions/contain more than 5 files not insessions/archived/? - Does the room main file exceed 150 lines?
Process rooms that meet either condition, one at a time. Report which rooms were found and ask for confirmation before proceeding if running interactively.
Step 2 — Read the room state
Read in this order:
- Room main file (
<room>/<room-name>.mdorREADME.md) - All unprocessed session logs: files in
<room>/sessions/that are not in<room>/sessions/archived/
Read session logs oldest-first (alphabetical by filename = chronological).
Do not read specialty files unless a Consolidation Note explicitly references them.
Step 3 — Extract consolidation candidates
For each session log, collect entries from the ### Consolidation Notes section.
Discard sessions with empty or blank Consolidation Notes.
Build a working list:
[ { source: "sessions/2026-02-01.md", note: "promote X to Overview section" },
{ source: "sessions/2026-02-15.md", note: "update Y in technical-gotchas.md" },
... ]
Resolve conflicts: if two notes contradict each other, the newer one wins. Flag irreconcilable conflicts for user review rather than silently choosing.
Step 4 — Merge into canonical files
For each consolidation candidate:
- Identify the target canonical file (room main file or a specialty file).
- Read the target file if not already loaded.
- Apply the change:
- New fact → add to the appropriate section
- Updated fact → edit the existing entry in place; remove the old version
- Superseded entry → delete the outdated content entirely
- Do not append alongside old content — canonical files must stay authoritative.
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.
- 3d ago Changed · +22 lines d7a906d141a7
- 11d ago First seen · 148 lines · 89 tokens per session scan A fd958a119d84
locus-consolidate is a skill published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,337 once invoked, about $0.0004 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.