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 Jiangxianze/spring-agent-skills --skill spring-ai-tool-reviewergit clone --depth 1 https://github.com/Jiangxianze/spring-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/jiangxianze/spring-agent-skills/spring-ai-tool-reviewer)<a href="https://agentmods.dev/skills/jiangxianze/spring-agent-skills/spring-ai-tool-reviewer"><img src="https://agentmods.dev/badge/skills/jiangxianze/spring-agent-skills/spring-ai-tool-reviewer/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/jiangxianze/spring-agent-skills/spring-ai-tool-reviewer"><img src="https://agentmods.dev/badge/skills/jiangxianze/spring-agent-skills/spring-ai-tool-reviewer.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 | $0.00065 | $0.00560 |
| Opus 5 | $0.00032 | $0.00280 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
spring-ai-tool-reviewer 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 12d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spring AI Tool Reviewer
Review the boundary where model-generated intent becomes application code. Treat every tool call as untrusted input and every tool result as potentially exposed to a model, trace, or user.
Establish the contract
- List each tool name, description, input, output, side effect, and downstream dependency.
- Identify the caller, tenant, authenticated principal, and authorization boundary.
- Separate read-only tools from tools that mutate state, spend money, send messages, disclose data, or invoke infrastructure.
- State missing runtime context before assigning severity. Do not infer safety from a Java method signature alone.
Review workflow
- Check that the description is specific enough for correct selection and states important exclusions. Flag vague verbs such as "manage" or "process".
- Check every parameter for a useful description, validation, bounded size or range, canonical form, and safe default. Reject model-provided identity or tenant fields when trusted context should supply them.
- Trace authorization from the tool entry point to the protected resource. Verify object-level access, not only authentication.
- Classify side effects. Require explicit approval for high-impact or irreversible actions and bind approval to the exact normalized request.
- Require an idempotency strategy for retryable mutations. Check timeout, cancellation, rate limiting, and retry ownership for remote calls.
- Map predictable failures to stable, non-sensitive results. Do not return stack traces, credentials, access tokens, internal prompts, or unrestricted records.
- Confirm structured audit events include tool name, outcome, duration, principal, resource identifier, and correlation ID without raw secrets.
- Test malformed input, unauthorized access, duplicate delivery, timeout, downstream failure, approval mismatch, and redaction as applicable.
Output contract
Start with block, change required, safe with conditions, or low risk.
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.
- 12d ago First seen · 45 lines · 65 tokens per session scan A 6ec2078ac825
spring-ai-tool-reviewer is a skill published in the GitHub repository Jiangxianze/spring-agent-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 560 once invoked, about $0.0003 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
spec-kitty-mission-review
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review"…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
simplify
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Reviews changed code…
adversarial-squad
Deploy a bounded, profile-loaded adversarial review squad at an SDD point-cut (post-spec, post-plan, post-tasks, pre-merge, or an ad-hoc decision) so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec…
spk-run-review-wp
Review a Spec Kitty work package through the runtime review surface and approve or reject with structured feedback.
spk-doctrine-bulk-edit
Recognize bulk-edit missions and apply occurrence classification guardrails before modifying many matching instances.