A command that refreshes a project's local Loci memory files, which store notes about the project's identity, progress, and connection to a central memory index.

Use it to update project memory from files such as the README, package configuration, Git settings, and directory structure.

It keeps project notes aligned with the current repository and shows what has changed without reading secrets or build files.

loci-scan — Command by codesstar

Install

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.

agentmods

npx agentmods add commands/codesstar/loci/loci-scan

Clone the repo

git clone --depth 1 https://github.com/codesstar/loci

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 492 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00492
Opus 5	$0.00000	$0.00246
Sonnet 5	$0.00000	$0.00098
Haiku 4.5	$0.00000	$0.00049

Measured 2d ago against content hash 0d29aecbfb52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loci-scan 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 2d 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.

templates/commands/loci-scan.md · 33 lines

What it actually says

Refresh the current project's local Loci memory.

This command updates the project repo's .loci/memory.md, .loci/profile.md, and .loci/progress/YYYY-MM.md according to their roles. Loci aggregates memory; it does not own it, so the brain keeps only a one-line index in projects/index.md.

Steps:

Check connection: Read .loci/memory.md in current directory. If not found, offer once at the end of the exchange: "这个项目还没有本地记忆。要不要我帮你在这里留个记忆？" If the user says yes, follow the "Connecting a serious project" rule in the main instructions.
Get brain path from .loci/memory.md frontmatter (brain: ...) and locate the brain index at <brain>/projects/index.md.
Refresh the local project memory from the repo:
- Read identity files (CLAUDE.md, README.md, package.json/pyproject.toml/etc., .git/config, LICENSE)
- Scan directory skeleton (tree -L 2)
- Extract structured data deterministically
- Generate AI one-line summary
- Never read .env, secrets, node_modules, build outputs, or private credentials
Compare with existing .loci/memory.md:
- Show what changed (e.g. "Tech stack updated: added Prisma", "Scale changed: medium → large")
- Preserve user-written Goal / Current State / Now / Next unless the change is clear
- Append project progress to .loci/progress/YYYY-MM.md
- Put stable attributes in .loci/profile.md
Write updated .loci/memory.md, .loci/profile.md, and .loci/progress/YYYY-MM.md as needed
Update brain index only if needed: If the one-line essence or status changed, update the project's entry in projects/index.md. Do not copy the full project memory into the brain.
Confirm: Show summary of changes or "Project memory is up to date, no changes detected."

Flags

--all: Run from brain directory to review projects listed in projects/index.md. Only open repos that are relevant or explicitly requested. Shows a summary table at the end.

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.

2d ago First seen · 33 lines · 0 tokens per session scan A 0d29aecbfb52

Subscribe to this mod's changes

loci-scan is a command published in the GitHub repository codesstar/loci (99 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 492 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.

Memory and context ai claude-code open-source personal-ai

loci-scan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Flags

What this file has done since we first saw it

Other commands, from other repositories

release-note-csoar

doc

wf-ads

claude-tracker

oss

doncheli-status