Borrowing it
Nothing to install: this file belongs to kivo360/OmoiOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kivo360/OmoiOS/main/.claude/skills/litho-budgeted-analysis/SKILL.mdgit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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/kivo360/omoios/litho-budgeted-analysis)<a href="https://agentmods.dev/skills/kivo360/omoios/litho-budgeted-analysis"><img src="https://agentmods.dev/badge/skills/kivo360/omoios/litho-budgeted-analysis/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/kivo360/omoios/litho-budgeted-analysis"><img src="https://agentmods.dev/badge/skills/kivo360/omoios/litho-budgeted-analysis.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 | $0.00090 | $0.01155 |
| Opus 5 | $0.00045 | $0.00577 |
| Sonnet 5 | $0.00018 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
litho-budgeted-analysis 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Litho Budgeted Analysis
Create a fast, repo-local Litho run plan without changing the user's global model choice.
Workflow
- Profile the repo.
- Detect the effective global Litho config path if possible.
- Inspect
.litho/cachefreshness. - Generate
litho.local.tomlin the target repo. - Prefer a direct run.
- Use filtered-copy mode only when the repo is too large for the time budget.
Scripts
0. Use the one-file local launcher
If you want the simplest possible local test, run exactly one file:
bash scripts/run_local_litho.sh /path/to/repo 15
That script:
- runs the full budgeted Litho workflow for the target repo
- streams progress in the current terminal
- writes
.litho/run.log - writes
.litho/run-status.json
If you want a detached background run instead:
bash scripts/run_local_litho.sh /path/to/repo 15 --detach
Then watch progress with:
bash scripts/watch_litho_progress.sh /path/to/repo
1. Profile the repo
Run:
bash scripts/uv_run.sh scripts/profile_repo.py --repo-path /path/to/repo
This returns JSON including:
- tracked file count
- source-like file count
- total/source-like bytes
- largest directories
- cache presence/freshness
- detected global Litho config path
- repo class (
small,medium,large,very-large)
2. Generate the local config
Run:
bash scripts/uv_run.sh scripts/generate_litho_config.py --repo-path /path/to/repo
Behavior:
- writes
/path/to/repo/litho.local.toml - preserves the user's existing provider/model settings
- only tunes safe runtime knobs like exclusions, boundary settings, chunking, and concurrency
- does not overwrite the global config
If automatic global-config detection is wrong or unavailable, pass it explicitly:
bash scripts/uv_run.sh scripts/generate_litho_config.py --repo-path /path/to/repo --global-config /path/to/global/litho.toml
3. Run Litho with a time budget
Run:
bash scripts/uv_run.sh scripts/run_litho_analysis.py --repo-path /path/to/repo --time-budget-minutes 15
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/heuristics.md 3.4 KB
- scripts/_litho_common.py 12 KB runs code
- scripts/generate_litho_config.py 6.5 KB runs code
- scripts/profile_repo.py 809 B runs code
- scripts/run_litho_analysis.py 6.0 KB runs code
- scripts/run_local_litho.sh 507 B runs code
- scripts/uv_run.sh 443 B runs code
- scripts/watch_litho_progress.sh 937 B runs code
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.
- 12d ago First seen · 154 lines · 90 tokens per session scan A 68dc66ae4d7e
litho-budgeted-analysis is a skill published in the GitHub repository kivo360/OmoiOS (77 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,155 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
self-awareness
Use when the user asks about Archie itself — what Archie is, how it works, what it can or cannot do, what agents or domains exist, how plugins work, how requests get handled, why something behaves a certain way, what integrations are available, or whether Archie can change itself. Triggers on phrases like "what can…
writing-plugins
Read this before authoring or substantially changing a plugin, agent, or skill for Archie. It's the conceptual playbook for building plugins that fit Archie's multi-agent, single-orchestrator model — what a plugin must respect, why every plugin usually needs an orchestrator-facing skill, and how to think about agents…
thread-conduct
Use before posting anywhere outside this task's own thread, or when deciding how much to post inside it. Covers keeping one task in one thread, what to do with a finding that belongs to another team, when a cross-channel post is allowed and how small it must be, how much traffic a thread should carry, and how to…
triggers
Set up, list, or manage triggers — persistent "do Y when X happens" rules. Use when someone asks Archie to do something on a schedule ("every weekday at 9am…", "every morning post…", "remind the channel weekly…"), to react to new messages in a channel ("whenever someone posts X in.
trigger-task
Use when this task was started by a trigger and you have been given a trigger directory — the one place that survives from one fire of that trigger to the next. Covers reading what an earlier fire left before you start work, what is worth leaving behind so a later fire continues instead of repeating, keeping the…
engineering-pr
Pull request lifecycle management. Use when you need to create a PR, handle PR reviews, resolve merge conflicts, or manage the PR-to-merge workflow. Extends the engineering skill with GitHub-specific tools and decision framework.