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 gopherguides/gopher-ai/plugin install go-workflowWrote 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/gopherguides/gopher-ai/address-review)<a href="https://agentmods.dev/skills/gopherguides/gopher-ai/address-review"><img src="https://agentmods.dev/badge/skills/gopherguides/gopher-ai/address-review.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.03755 |
| Opus 5 | $0.00031 | $0.01878 |
| Sonnet 5 | $0.00012 | $0.00751 |
| Haiku 4.5 | $0.00006 | $0.00376 |
Grade A, and why
address-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 4d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address PR Review Comments
Plugin Resource Resolution
<PLUGIN_ROOT> is notation. Replace it with a concrete absolute plugin root before every resource read or command:
- Codex: Start from the directory containing the absolute selected
SKILL.mdpath, then ascend two directories (skills/<name>-> plugin root). - Claude Code: Bind it to the injected
${CLAUDE_PLUGIN_ROOT}value.
Before requesting decisions or delegating work, read
<PLUGIN_ROOT>/lib/driver-interaction.md and follow its
cross-platform capability-binding rules.
Read <PLUGIN_ROOT>/lib/decision-gates.md before resolving any workflow
choice.
Bind the invocation arguments as SKILL_ARGS for $go-workflow:address-review by
reading <PLUGIN_ROOT>/lib/skill-arguments.md with this Claude Code compatibility payload:
$ARGUMENTS
source "<PLUGIN_ROOT>/lib/github-rest.sh"
Output Durability
Replies to review comments and any new commit messages describe what behavior changed and why, not file paths or line numbers. A reviewer reading the reply six months later, after the file in question has moved, must still understand what was fixed.
If SKILL_ARGS is empty or not provided:
Auto-detect PR from current branch:
CURRENT_CHECKOUT_ROOT=$(git rev-parse --show-toplevel)
WORKTREE_PATH="$CURRENT_CHECKOUT_ROOT"
CURRENT_PR_JSON=$(cd "$WORKTREE_PATH" && github_current_pr 2>/dev/null) || true
jq -r '.number' <<< "$CURRENT_PR_JSON" 2>/dev/null
If no PR is found, display usage:
Claude Code: /go-workflow:address-review [PR-number] [--no-watch]
Codex: $go-workflow:address-review [PR-number] [--no-watch]
Example: /address-review 123 or just /address-review on a PR branch. Add --no-watch to exit after one fix cycle instead of watching for bot re-reviews.
This is a missing-intent gate. Request: "No PR was found for the current branch. What PR number should I address?" If structured input is unavailable, ask in the final response and stop before loop initialization or a completion claim.
What ships with it
9 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.
- 4d ago Changed · +13 lines 995b9a8a4d12
- 8d ago First seen · 335 lines · 62 tokens per session scan A 0bb5a7f2dd55
address-review is a skill published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 3,755 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 2026-08-30.
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…