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 akshan-main/review-by-opp --skill fixgit clone --depth 1 https://github.com/akshan-main/review-by-oppWrote 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/akshan-main/review-by-opp/fix)<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/fix"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/fix/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/akshan-main/review-by-opp/fix"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/fix.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 | $0.00032 | $0.00575 |
| Opus 5 | $0.00016 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
review-by-opp:fix 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 10d 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.
What it actually says
You are addressing Codex review findings. You are the builder - fix what needs fixing.
What to do
-
Load the ledger:
- Read
reviews/current.json - If missing, tell user: "No active session. Run
/review-by-opp:startfirst."
- Read
-
Show open findings:
- List all findings with status
open, grouped by severity (critical first) - For each, show: ID, severity, category, title, file, line, description, suggested_fix
- List all findings with status
-
Address findings one by one: For each finding, you MUST do one of these - no exceptions:
a. Fix it → Make the code change, then update the finding:
- Set
statustofixed - Set
resolution_noteto a brief description of what you changed - The fix must be verifiable (actual file changes, not just claiming it's done)
b. Mark as won't_fix → If the finding is intentional or acceptable:
- Set
statustowont_fix - Set
resolution_noteexplaining why
c. Mark as not_reproducible → If you cannot reproduce the issue:
- Set
statustonot_reproducible - Set
resolution_notewith your investigation
d. Mark as needs_context → If you need more information:
- Set
statustoneeds_context - Set
resolution_notedescribing what context is needed
e. Mark as duplicate → If this duplicates another finding:
- Set
statustoduplicate - Set
duplicate_ofto the other finding's ID
- Set
-
Update the ledger:
- Write updated findings back to
reviews/current.json - Every finding must have a resolution state - you cannot skip any
- Write updated findings back to
-
Report progress:
- Show how many findings were resolved this pass
- Show remaining open findings
- If blocking findings remain: "Run
/review-by-opp:fixagain or/review-by-opp:reviewfor another Codex pass" - If no blocking findings: "Ready for another review round (
/review-by-opp:review) or finalize (/review-by-opp:finalize)"
CRITICAL: You MUST NOT claim "all fixed" unless every finding has an explicit resolution state. The ledger enforces this - hand-waving is not allowed.
$ARGUMENTS
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.
- 10d ago First seen · 56 lines · 32 tokens per session scan A 54c5ab1fe6f4
review-by-opp:fix is a skill published in the GitHub repository akshan-main/review-by-opp (6 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 575 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
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
flow-next-plan-review
Carmack-level review of a flow-next spec or plan via the configured backend. Use when asked to review a plan or spec.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.