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 jscraik/Agent-Skills --skill sy-reviewgit clone --depth 1 https://github.com/jscraik/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/jscraik/agent-skills/sy-review)<a href="https://agentmods.dev/skills/jscraik/agent-skills/sy-review"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/sy-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/jscraik/agent-skills/sy-review"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/sy-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 | $0.00042 | $0.00629 |
| Opus 5 | $0.00021 | $0.00315 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
sy-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 8d 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.
This is a copy
86% identical to sy-execution-plan — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SynAIpse Harness Review
When to use
Use when the user asks for review, PR readiness, risk assessment, blocker identification, or post-work verification.
Required inputs
- User request or routed handoff naming this stage.
- Current repository, branch, artifact, tracker, PR, validation, and session evidence when available.
- The previous-stage artifact when this stage depends on one.
Deliverables
- A stage result with schema_version, stage, status, evidence_refs, blocked_by, and next_stage.
- Exact validation status using pass, fail, or blocked.
- A handoff that names what is proven and what remains unproven.
Procedure
- Restate the active repo, branch, requested stage, and available evidence.
- Check the previous-stage artifact or explain why it is not required.
- Perform only the work owned by review.
- Record evidence refs and classify each lane as pass, fail, blocked, or not_checked.
- Emit the next-stage handoff to eval-report or a blocker with the smallest recovery step.
Validation
Fail fast: stop at the first failed required gate, classify the blocker, and do not proceed to downstream stages until the failure is resolved or explicitly waived. Run the smallest relevant local check for changed files; for package-level changes, run plugin validation and SDK proof commands from the repository wrapper.
Handoff
Return the stage artifact or blocker, then hand off to eval-report only after this stage's exit criteria are satisfied.
Failure modes
- Missing previous-stage artifact: block and request or create the required artifact through the owning stage.
- Conflicting evidence lanes: route to reconcile.
- Repeated failure or durable learning: route to reinforce.
- Requested action exceeds authority: block with the required authorization.
Gotchas
-
Do not use this stage to skip the lifecycle, merge evidence lanes, mutate external systems without explicit authorization, or complete another stage's exit criteria.
-
Similar legacy names may exist in caches or older Harness Engineering packages; do not expose them as SynAIpse active skills.
-
A local artifact can explain work, but it does not prove remote PR, CI, tracker, or deployment state.
-
If multiple stages seem plausible, route to sy-reframe instead of doing blended stage work.
What ships with it
7 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.
- 8d ago First seen · 68 lines · 42 tokens per session scan A 54fe8b0735be
sy-review is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 42 tokens to every session and 629 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to sy-execution-plan, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
prepare-pr
A pull-request preparation workflow for a software branch. A pull request is a request for teammates to review and merge a set of code changes.
refactoring
Safely refactor code while maintaining behavior. Use when improving code structure, reducing duplication, extracting functions, or modernizing legacy code.
code-review
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
pr-review-expert
Review GitHub PRs or GitLab MRs for correctness, security, compatibility, and affected test coverage, with actionable evidence tied to the diff.