Borrowing it
Nothing to install: this file belongs to OutlitAI/outlit-sdk. 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/OutlitAI/outlit-sdk/main/.agents/skills/running-subagent-reviews/SKILL.mdgit clone --depth 1 https://github.com/OutlitAI/outlit-sdkWrote 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/outlitai/outlit-sdk/running-subagent-reviews)<a href="https://agentmods.dev/skills/outlitai/outlit-sdk/running-subagent-reviews"><img src="https://agentmods.dev/badge/skills/outlitai/outlit-sdk/running-subagent-reviews/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/outlitai/outlit-sdk/running-subagent-reviews"><img src="https://agentmods.dev/badge/skills/outlitai/outlit-sdk/running-subagent-reviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 151 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.01229 |
| Opus 5 | $0.00023 | $0.00615 |
| Sonnet 5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
running-subagent-reviews 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Subagent Reviews
Overview
Run calibrated fresh-context reviewer passes, then reconcile the findings into concrete fixes or explicit non-blocking risks. A subagent review is not a single broad "looks good" check; it is a set of independent, lens-specific reviews over raw artifacts.
Workflow
- Identify the artifact under review: design/spec/plan, implementation diff, PR, fix diff, writing draft, or release/rollout checklist.
- Gather raw artifacts reviewers can inspect without chat history:
- requirements, plan, or spec text
- file paths or git range (
BASE_SHA..HEAD_SHA) when code exists - diff stat and relevant full diff
- verification already run, with command names and result summaries
- known constraints, target branch, rollout requirements, and explicit user concerns
- Choose distinct review lenses. Do not send multiple reviewers the same vague prompt.
- Spawn the requested number of reviewers. If the user did not specify a count, use 2 reviewers for narrow work and 3-4 for broad cross-surface work.
- Reconcile findings yourself:
- Fix valid Critical issues before proceeding.
- Fix valid Important issues unless there is a concrete reason to defer.
- Treat Minor issues as optional notes.
- Push back on incorrect findings with code, requirements, or test evidence.
- Re-run relevant verification after fixes.
- Run a follow-up review only on materially changed risk areas or the fix diff. Do not run identical rounds over unchanged artifacts unless the user explicitly asked for them.
- Stop when the requested lenses are covered and no valid Critical or Important issues remain, or when unresolved items are explicitly called out as residual risk.
Lens Selection
For design or implementation plans:
- architecture and sequencing
- data model, migrations, permissions, and compatibility
- API/runtime contracts and cross-repo drift
- verification, rollout, and operational recovery
For implementation diffs before PR:
- product and requirements correctness
- production risk: auth, security, data integrity, migrations, rollback, observability
- architecture, maintainability, concurrency, and performance
- tests and verification quality
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 · 155 lines · 47 tokens per session scan A ef86bc1e1f38
running-subagent-reviews is a skill published in the GitHub repository OutlitAI/outlit-sdk (6 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 1,229 once invoked, about $0.0002 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
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
code-simplifier
Post-session code review and cleanup against a working tree of changes. Analyzes git diff to simplify, consolidate, and align changed code with the existing codebase — modernize syntax, remove unnecessary complexity, consolidate duplicated logic, catch efficiency issues. Use after a substantive working session, or…
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.
code-review
Review ServiceNow server-side scripts for ES5 violations, ACL/injection/XSS issues, N+1 queries, missing setLimit/error handling, hard-coded sysids, and business-rule recursion risks.
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.