Borrowing it
Nothing to install: this file belongs to themoment-team/datagsm-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/themoment-team/datagsm-server/master/.agents/skills/resolve-reviews/SKILL.mdgit clone --depth 1 https://github.com/themoment-team/datagsm-serverWrote 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/themoment-team/datagsm-server/resolve-reviews)<a href="https://agentmods.dev/skills/themoment-team/datagsm-server/resolve-reviews"><img src="https://agentmods.dev/badge/skills/themoment-team/datagsm-server/resolve-reviews/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/themoment-team/datagsm-server/resolve-reviews"><img src="https://agentmods.dev/badge/skills/themoment-team/datagsm-server/resolve-reviews.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 | $0.00037 | $0.01090 |
| Opus 5.5 | $0.00015 | $0.00436 |
| Sonnet 5.5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade C, and why
resolve-reviews scanned grade C with 1 finding 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 19d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .pr-tmp How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1 — Collect PR Data
bash .agents/skills/resolve-reviews/scripts/get-pr-data.sh
Output files:
.pr-tmp/pr_comments.json— inline review comments (id, path, line, body, user).pr-tmp/pr_changed_files.txt— changed files.pr-tmp/pr_commits.txt— commits in this PR.pr-tmp/pr_diff.txt— full diff
Also fetch repo and PR metadata:
gh repo view --json nameWithOwner -q .nameWithOwner
gh pr view --json number,baseRefName -q '{number: .number, base: .baseRefName}'
Step 2 — Assess Each Comment
Read AGENTS.md before assessing comments. Discover the shared convention files:
rg --files --hidden .claude/rules -g '*.md'
Read the rules whose paths match the reviewed files. Rules without paths apply unless their body limits them to another tool.
Rule priority: AGENTS.md > applicable .claude/rules/** > .gemini/styleguide.md > CONTRIBUTING.md
For each comment in pr_comments.json, apply the following layered judgment criteria:
Judgment criteria (priority order)
- Project conventions (primary): apply
AGENTS.mdand the shared rules loaded above; consultCONTRIBUTING.mdfor supplementary guidance- DTO annotation rules, commit scope, logging style, exception message format, etc.
- Language/framework best practices (secondary): Kotlin official guide, Spring Boot recommendations
- Apply only when no matching project rule exists
Verdicts
- VALID: reviewer is correct → attempt auto code fix
- INVALID: reviewer is wrong with a clear refutation → skip, post refutation reply
- PARTIAL: intent is correct but application method or scope is ambiguous → confirm with AskUserQuestion
Always cite a specific source in the rationale (e.g. .claude/rules/logging.md §Style, Kotlin: prefer val over var).
Step 3 — Act on Each Verdict
VALID → Auto fix
- Read the target file with the Read tool
- Apply the reviewer's concern with the Edit tool
- If the changes have not been committed yet, commit them
- Record the short commit hash for use in Step 5:
git rev-parse --short=7 HEAD
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.
- 19d ago Changed · +10 lines e56d316954d0
- 29d ago First seen · 115 lines · 37 tokens per session scan C 75be0cc3a165
resolve-reviews is a skill published in the GitHub repository themoment-team/datagsm-server (29 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,090 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
resolve-reviews compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| resolve-reviewsthemoment-team/datagsm-server | Skill | 29 | yesterday | MIT | C | 37 | Claude Code |
| plugin-code-review-orchestratedexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| review-async-lifecycleexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 66 | Claude Code, Codex |
| review-findings-validatorexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 77 | Claude Code, Codex |
| review-psi-vfs-indexingexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 73 | Claude Code, Codex |
| review-ui-leak-via-listenersexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 99 | Claude Code, Codex |
| review-ui-platformexplyt/spring-plugin | Skill | 167 | yesterday | Apache-2.0 | A | 74 | Claude Code, Codex |