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 lossless-group/lossless-agent-skills --skill pseudomonoreposgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/pseudomonorepos)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/pseudomonorepos"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/pseudomonorepos/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/lossless-group/lossless-agent-skills/pseudomonorepos"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/pseudomonorepos.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 | $0.00182 | $0.05226 |
| Opus 5 | $0.00091 | $0.02613 |
| Sonnet 5 | $0.00036 | $0.01045 |
| Haiku 4.5 | $0.00018 | $0.00523 |
Grade A, and why
pseudomonorepos 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 11d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pseudomonorepos
Not a true monorepo. Not loosely coupled either. A parent repo that adds children (often as git submodules) primarily so the parent can host a
context-v/that aggregates context across them.
When to use this skill
- Working anywhere under
~/code/lossless-monorepo/or any of its descendants - Starting any task — coding, writing a spec, drafting a prompt, debugging — that might overlap with prior work elsewhere in the tree
- Scaffolding a new sub-project (where does it go? does it deserve its own pseudomonorepo level?)
- User mentions "pseudomonorepo", "submodule", "the tree", or any of the named children
- Considering whether to add a folder/repo as a submodule vs. inline
The behavioral core (this is the actual skill)
Don't rush into creating. Before writing a new spec, prompt, blueprint, doc, or substantial code:
- Walk the tree up. Identify which pseudomonorepo level you're in. Walk to the root.
- Search prior work at every level's
context-v/:- Specs, blueprints, prompts, explorations, issues
- Filenames (use grep/find by topic keywords)
- Frontmatter tags
- Surface what you find to the user. "I see related work in
astro-knots/context-v/blueprints/X.mdandlossless-monorepo/context-v/explorations/Y.md— should we extend those, link to them, or write something new?" - Cross-reference, don't duplicate. Link to prior work using
[[wikilinks]]. Re-stating without linking is a smell.
The escape hatch: ship fast
Sometimes assembling patterns, finding prior work, and writing context-v files slows speed to ship. That's a real tradeoff. When the user signals "just ship it":
- Acknowledge you're shortcutting the search-first discipline
- Ship
- Log refactor debt in the relevant
context-v/issues/orcontext-v/explorations/as a one-liner: "Shipped X without searching for prior patterns. Refactor candidate: connect to existing work in [[…]]?" - Don't pretend you did the search. Honesty about the shortcut is what makes the refactor possible.
What ships with it
6 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.
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.
- 11d ago First seen · 362 lines · 182 tokens per session scan A 82ae825a145c
pseudomonorepos is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 182 tokens to every session and 5,226 once invoked, about $0.0009 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
github-commander
Structured workflows for GitHub issues, PRs, milestones, and code audits with validation gates and HITL checkpoints. Use when assigned a GitHub issue, reviewing a PR, sprinting through a milestone, updating dependencies, or running code audits. Also use when asked to "triage an issue", "review a PR", or "update deps".…
gitlab
Specialized assistant skill for managing repositories and CI/CD in GitLab. Activate when the user asks about GitLab projects or repositories, wants to see merge requests or pipelines, needs to search code or files, asks about CI/CD status or job logs, or wants to browse repository contents. Mentions "GitLab", "glab"…
version
Lock bundles with semantic versioning. Guides through version selection, updates files, and integrates with git.
review-before-commit
Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.
github-repo-setup
Reusable scaffold for public TypeScript/Node.js repositories under a target organization. Use when creating a new GitHub repository to generate all community standards, CI/CD, config files, labels, and topics in one pass.
gsd-undo
Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.