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 VirajMishra1/loadout --skill loadout-curatorgit clone --depth 1 https://github.com/VirajMishra1/loadoutWrote 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/virajmishra1/loadout/loadout-curator)<a href="https://agentmods.dev/skills/virajmishra1/loadout/loadout-curator"><img src="https://agentmods.dev/badge/skills/virajmishra1/loadout/loadout-curator/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/virajmishra1/loadout/loadout-curator"><img src="https://agentmods.dev/badge/skills/virajmishra1/loadout/loadout-curator.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 | $0.00069 | $0.00844 |
| Opus 5.5 | $0.00028 | $0.00338 |
| Sonnet 5.5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
loadout-curator 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loadout Curator
Match the active skill set to the repository in front of you. Too few skills and the agent lacks context; too many and every prompt carries weight it does not need.
This skill wraps the loadout CLI so the catalog, provenance, and safety
findings stay current rather than being copied into this file.
Prerequisite
loadout --version
If that fails, tell the user to install it (npm install --global loadout-ai)
and stop; do not guess at catalog contents.
Starting work in a repository
Read what the codebase actually is before suggesting anything:
loadout recommend --project .
This prints detected signals (languages, frameworks, test runners) and rule-based suggestions with a confidence label. The signals are the useful part — they tell you what the repository is without you reading every file.
Report the detected stack first, then the suggestions worth acting on. Skip low-confidence suggestions unless the user asks for the full list.
recommend reads the project and the catalog. It does not prove quality, and it
says so; repeat that framing rather than presenting suggestions as verified.
Proposing an active set
loadout optimize --project .
This proposes which already-downloaded library skills should be active here.
Use it when the user has a Maximum-mode library, or after recommend shows the
project needs something different from what is on.
Present the proposal as a diff in plain words — what turns on, what turns off,
and why — before the user approves. Both commands are read-only until --yes.
Installing something new
loadout setup --mode custom --package <id> # preview
loadout setup --mode custom --package <id> --yes # apply
Never run the --yes form on your own initiative. Show the preview, summarize
what it adds and to which agents, and let the user approve. Loadout snapshots
before writing, and loadout rollback undoes the last apply — say so, because
it lowers the cost of trying something.
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 First seen · 106 lines · 69 tokens per session scan A 7522c5964163
loadout-curator is a skill published in the GitHub repository VirajMishra1/loadout (5 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 844 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 2026-09-05.
Other skills, from other repositories
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.