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 finalizegit 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/finalize)<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/finalize"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/finalize/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/finalize"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/finalize.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 | $0.00026 | $0.00586 |
| Opus 5 | $0.00013 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
review-by-opp:finalize 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
Finalize the review-by-opp session. This is the exit gate.
What to do
-
Load the ledger:
- Read
reviews/current.json - If missing, tell user: "No active session. Run
/review-by-opp:startfirst."
- Read
-
Run the exit gate check: Check ALL of these conditions:
a. No blocking findings open:
- Get all findings where
status === "open"and severity is inblockingSeverities - If any exist: BLOCK. List them and say: "Cannot finalize. {N} blocking finding(s) still open."
b. No findings without resolution state:
- Every finding must have a status other than just existing with no decision
- If any finding has
status === "open"and is blocking: BLOCK.
c. No false completion claims:
- Any finding marked
fixedMUST have aresolution_note - If any
fixedfinding lacks a note: BLOCK. "Finding {id} is marked fixed but has no resolution note."
- Get all findings where
-
If blocked:
- List all blocking reasons
- Tell user: "Use
/review-by-opp:fixto resolve remaining findings." - Do NOT finalize.
-
If clear to finalize:
- Determine the final verdict:
clean- no open findings at allclean_with_accepted_exceptions- only non-blocking findings remain openmax_rounds_reached- max rounds hit (but no blocking findings)
- Set
final_verdictin the ledger - Write the final state to
reviews/current.json
- Determine the final verdict:
-
Report final verdict: Show a summary:
## Final Verdict: {VERDICT} - Rounds completed: {N} - Total findings: {N} - Fixed: {N} - Won't fix: {N} - Not reproducible: {N} - Needs context: {N} - Duplicate: {N} - Superseded: {N} - Still open (non-blocking): {N} -
Session is now closed. Tell user: "Session finalized. To start a new session, run
/review-by-opp:start."
CRITICAL: This is the stop gate. You MUST NOT bypass it. If blocking findings remain, finalization MUST fail. This is the entire point of review-by-opp.
$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 · 64 lines · 26 tokens per session scan A b9b86f6ea83c
review-by-opp:finalize is a skill published in the GitHub repository akshan-main/review-by-opp (6 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 586 once invoked, about $0.0001 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.