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 flurdy/agent-skills --skill total-reviewgit clone --depth 1 https://github.com/flurdy/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/flurdy/agent-skills/total-review)<a href="https://agentmods.dev/skills/flurdy/agent-skills/total-review"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/total-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/flurdy/agent-skills/total-review"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/total-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.04280 |
| Opus 5 | $0.00024 | $0.02140 |
| Sonnet 5 | $0.00010 | $0.00856 |
| Haiku 4.5 | $0.00005 | $0.00428 |
Grade A, and why
total-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 yesterday.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Total Review
A local, bounded pre-PR gauntlet in increasing cost order. Compose installed skills, use explicit manual review where the host lacks a suitable reviewer, and keep one authoritative ledger of scope, fixes, gate evidence, and findings. A command's absence or an old clean result is never clearance.
Use before a non-trivial PR or after a substantial refactor. For a trivial change use clean-code;
for unfinished work use verify-task; for someone else's PR use review-pr. This skill does not
commit, push, publish PR feedback, or change the installed client configuration.
Usage
/total-review # Branch changes plus selected local work
/total-review --uncommitted # Local changes; initial HEAD is the fixed base
/total-review --pr <N> --repo <owner/repo>
/total-review --skip-external # Explicit local-only coverage
/total-review --no-iterate # One pass; no fix/review loop
/total-review --inline-findings # No Beads writes
Flags compose; reject conflicting scopes, missing values, duplicate or unknown flags. --pr requires
an explicit repository or a verified current-checkout repository identity; never resolve a bare PR
number across repositories. No resume or halt-override flag exists.
0. Resolve capabilities and scope
Portable composition
Read the installed skill by name and follow its instructions with the ledger's exact scope packet.
Use the native skill loader when exposed; otherwise read ~/.agents/skills/<name>/SKILL.md and
execute its instructions using the current harness's tools. Do not type a slash command into a shell.
| Client | Shared skill resolution |
|---|---|
| Pi | Native skill loading when available; otherwise read the shared SKILL.md with Read. |
| Claude Code | Native Skill tool when available; otherwise read the shared SKILL.md with Read. |
| Codex | Native skill loading when available; otherwise read the shared SKILL.md with the file-reading tool. |
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.
- yesterday Changed · -75 lines · -40 tokens per session 9ae1da5f8a32
- 9d ago First seen · 369 lines · 89 tokens per session scan A 7d14c7ab08d6
total-review is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 4,280 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…