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 IsaiaScope/ai --skill iso-reviewgit clone --depth 1 https://github.com/IsaiaScope/aiWrote 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/isaiascope/ai/iso-review)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-review"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-review/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/isaiascope/ai/iso-review"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-review.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 | $0.00000 | $0.03355 |
| Opus 5 | $0.00000 | $0.01677 |
| Sonnet 5 | $0.00000 | $0.00671 |
| Haiku 4.5 | $0.00000 | $0.00335 |
Grade A, and why
iso-review 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 5d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-review
Take the work sitting on this branch and make it better, then check it. Three phases, in one order:
| # | phase | what it asks | runs |
|---|---|---|---|
| 1 | architecture | is this the right shape? | here, in this session |
| 2 | simplify | can this read plainer? | here, in this session |
| 3 | review | is this wrong? | a subagent |
Invocation: /iso-review [--no-architecture] [--no-simplify] [--no-review].
All three run by default.
Mechanics live in skills/iso-review/scripts/review.sh. Run it by absolute
path. It gives you six verbs and no orchestration — the order below is the
orchestration.
| verb | does |
|---|---|
preflight |
stage, resolve the base, deal with staleness. Prints index= and base= |
scope [base] |
print what a run would act on, without acting and without spending a token. Without base it re-runs preflight, so it stages, and prints index= too |
skill-check <name>... |
is each phase's skill invocable by a model? Non-zero if any is blocked |
snapshot |
print a tree sha for the current working tree. One phase's undo point |
gate <name> [snap] |
run the repo's tests; on red, undo back to <snap>. Prints one phase= line. <snap> is also what files= is measured from |
report |
summary on stdin: echo it, and post it as one ticket comment |
The run
Preflight. review.sh preflight. Non-zero: print its message and stop.
Read the index=, base= and note= lines and leave them in the terminal.
They do not go in the report — see below.
Skill gate. review.sh skill-check improve-codebase-architecture simplify review.
A phase is its skill, so this asks whether each one can actually be invoked by a model. It reports one line per name:
| state | means | do |
|---|---|---|
ok |
one copy on disk, invocable | carry on |
ok copies=N |
several copies, all invocable | carry on; N>1 is worth a glance, since you cannot tell which one answers |
builtin |
no file on disk | carry on — the harness ships skills with no SKILL.md. Also how a mistyped phase name looks, so read it |
blocked |
every copy carries disable-model-invocation: true |
stop and fix, below |
split |
copies disagree — some blocked, some not | stop. Which one answers decides whether the phase runs at all, and nothing here can predict the resolution order |
What ships with it
2 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.
- 5d ago Changed · +60 lines 577ed0b1b5f4
- 10d ago First seen · 218 lines · 0 tokens per session scan A 158589efe28e
iso-review is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,355 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 2026-08-31.
Other skills, from other repositories
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
comet-github-pr-review
A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
agent-cross-review
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback. Use when one agent reviews another's work, during handoffs, or when validating cross-cutting concerns.
ac-commit-manager
Manage git commits for autonomous coding. Use when committing feature implementations, creating descriptive commits, managing git workflow, or handling version control.