Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add infraspecdev/tesseract/plugin install shieldWrote 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/infraspecdev/tesseract/review)<a href="https://agentmods.dev/skills/infraspecdev/tesseract/review"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/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/infraspecdev/tesseract/review"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/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 | $0.00033 | $0.02598 |
| Opus 5.5 | $0.00013 | $0.01039 |
| Sonnet 5.5 | $0.00007 | $0.00520 |
| Haiku 4.5 | $0.00003 | $0.00260 |
Grade A, and why
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 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Orchestrator
Output Path — MANDATORY
All review output goes into a per-run, date-keyed folder under the feature's reviews/code/ directory:
{output_dir}/{feature}/reviews/code/{date}{_counter}/ ← {review_dir}
├── summary.md ← {review_summary} (consolidated findings, main output)
├── changes.md ← applied-fixes log (side-artifact, written after step 9)
└── detailed/
└── <agent>.md ← {review_detailed} (one per dispatched agent)
{output_dir}/{feature}/outputs/reviews/code/{date}{_counter}/ ← {review_outputs_dir}
├── summary.html ← {review_summary_html}
└── detailed/
└── <agent>.html ← {review_detailed_html} (one per agent)
Where {output_dir} comes from .shield.json output_dir field (default docs/shield), {feature} is the feature folder name ({feature-name}-YYYYMMDD), {date} is today's ISO date (YYYY-MM-DD), and {_counter} is empty for the first run of the day or _2, _3, ... on same-day collisions. Numbered-run subfolders (code-review/{N}-{slug}/) are gone. Reviews never overwrite prior runs.
Resolving the counter: before writing, list {output_dir}/{feature}/reviews/code/ for entries matching today's date. If {date}/ does not exist, use _counter="". Otherwise, find the highest {date}_<N>/ and use _counter="_<N+1>". Do NOT use any other path or directory structure. The Write tool creates directories automatically.
When to Use
- After implementing a feature or story step
- When explicitly invoked via
/review - As the final review at the end of an implementation pipeline
When NOT to Use
- For plan review — use
plan-reviewskill instead - For a single specific reviewer — use
/review-security,/review-cost, etc.
Step Skeleton
At startup, call execute-steps to register these steps. Execute them in order, updating status after each.
| Step | Action | Condition | Mandatory |
|---|---|---|---|
| 1 | Load prior context (plan, research) | skip if none exists | No |
| 2 | Code correctness review | always | Yes |
| 3 | Domain-specific review | skip if no active domains | No |
| 4 | Dispatch agent reviewers | explicit/final review only | No |
| 5 | AC verification | skip if no plan.json | No |
| 6 | Merge + present findings | always | Yes |
| 7 | Apply selected fixes | always | Yes |
| 8 | Write summary + update manifest | always | Yes |
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 · 240 lines · 33 tokens per session scan A aa271b2de9cb
review is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,598 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…