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 agentmods add skills/choi138/toki/codex-review-loopnpx skills add choi138/toki --skill codex-review-loopgit clone --depth 1 https://github.com/choi138/tokiWrote 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/choi138/toki/codex-review-loop)<a href="https://agentmods.dev/skills/choi138/toki/codex-review-loop"><img src="https://agentmods.dev/badge/skills/choi138/toki/codex-review-loop.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 | $0.00098 | $0.02203 |
| Opus 5 | $0.00049 | $0.01102 |
| Sonnet 5 | $0.00020 | $0.00441 |
| Haiku 4.5 | $0.00010 | $0.00220 |
Grade A, and why
codex-review-loop 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 3d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toki Codex Review Loop
Run an rvw-compatible lane review, then apply the codex-lb-style approval, atomic-fix, verification, and bounded re-review loop.
Core Contract
- Treat every review request as read-only until the user explicitly approves a write mode.
- Never infer permission to edit or commit from phrases such as "review this"
or from a GitHub
@codex reviewrequest. - Never push, submit a GitHub review, comment, resolve threads, label, merge, or otherwise mutate remote state from this skill.
- Preserve unrelated staged, unstaged, and untracked changes. Never use
git reset,git checkout, or broad restoration to undo a finding fix. - Treat local usage logs, databases, audit findings, prompts, transcripts, and credentials as sensitive. Do not print raw matched diff content.
- Apply
project-conventionsand read its task-specific references before fixing Toki source, tests, resources, or project configuration. - Apply
.agents/conventions/git-workflow.mdbefore any commit. A commit requires explicit user authorization separate from review authorization.
Trust Boundary
Scope resolution runs before any review and must survive a hostile repository.
Treat this section as the contract a finding is measured against: report a
finding when it breaks an invariant below, and classify it wont_fix with this
section as the reason when it only restates a non-goal.
Untrusted Inputs
- Repository file contents and tree layout, including untracked and ignored paths.
- Repository Git configuration:
.git/config,.gitattributes,.gitmodules, and any configured hook or helper program. - The inherited
PATHand everyGIT_*environment variable. - Lane result JSON, including every path and line number it reports.
Enforced Invariants
- Only trusted executables run.
gitand the review binary resolve from the platform default path, never from an inheritedPATH, and the runner narrowsPATHbefore invoking any external command. - No repository-configured program executes. Content filters,
textconv, external diff,core.fsmonitor,core.hooksPath, and lazy fetch are overridden to inert values or the scope is refused. - Workspace confinement is derived from the filesystem, not from Git. The inventory walks the real tree from the repository root and validates every symbolic link target, so ignore rules and index modes cannot hide a path.
- Every scope fails closed. A submodule, embedded repository, escaping symlink, non-UTF-8 path, or unbounded inventory marks the scope unsafe and stops before Codex is invoked.
- Paths keep byte fidelity across process boundaries. Roots and path lists cross as NUL-terminated data and are never trimmed.
- Reported findings are untrusted data. A finding path must be repository-relative, free of NUL, and free of empty, current, or parent segments before it is used.
- The baseline lane is always on. A registry that marks it otherwise is rejected.
What ships with it
31 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.
- agents/openai.yaml 241 B
- references/lane-registry.json 6.6 KB
- references/lanes/baseline.md 679 B
- references/lanes/build-portability.md 742 B
- references/lanes/concurrency-lifecycle.md 784 B
- references/lanes/privacy-security.md 791 B
- references/lanes/remote-sync.md 840 B
- references/lanes/swiftui-architecture.md 793 B
- references/lanes/testing.md 792 B
- references/lanes/usage-pricing.md 792 B
- references/prompts/reviewer.md 1.9 KB
- references/schemas/review-findings.schema.json 1.7 KB
- references/verification.md 2.6 KB
- scripts/finding_grouping.py 1.1 KB runs code
- scripts/finding_validation.py 5.3 KB runs code
- scripts/lane_registry_validation.py 2.7 KB runs code
- scripts/merge_findings.py 8.7 KB runs code
- scripts/resolve_repo_root.py 597 B runs code
- scripts/resolve_review_scope.py 9.2 KB runs code
- scripts/review_git_process.py 8.1 KB runs code
- scripts/review_path_matching.py 1.0 KB runs code
- scripts/review_scope_git.py 8.3 KB runs code
- scripts/review_workspace.py 4.9 KB runs code
- scripts/run_review_lane.sh 5.8 KB runs code
- scripts/run_with_safe_git.py 993 B runs code
- tests/test_activation_hook.py 2.5 KB runs code
- tests/test_finding_merge.py 18 KB runs code
- tests/test_path_resolution.py 4.4 KB runs code
- tests/test_runner_contract.py 20 KB runs code
- tests/test_scope_routing.py 15 KB runs code
- tests/test_scope_security.py 33 KB runs code
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.
- 3d ago First seen · 226 lines · 98 tokens per session scan A c82467ea62e2
codex-review-loop is a skill published in the GitHub repository choi138/toki (9 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 2,203 once invoked, about $0.0005 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
issue-brief
Explain a GitHub issue, discussion, or feature request in plain language before deciding whether to build it. Covers what the reporter actually wants, a numbered walkthrough of the failure using real hostnames/ports/endpoints, how the code behaves today with file:line anchors, what implementing it would take, and the…
bug-audit
Weekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries). Fans out Sonnet scanners + Opus deep auditors, adversarially verifies every finding, files GitHub issues for confirmed critical/high bugs. Trigger: /bug-audit.
telnyx-ai-inference-curl
Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides REST API (curl) examples.
telnyx-ai-assistants-go
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
telnyx-email-domains-curl
Manage email sending domains, verify DNS records (SPF, DKIM, DMARC, MX), check domain health, and configure domain-level webhooks for delivery events.
telnyx-email-inbound-curl
Manage email inboxes, list and search inbound messages, threads, sender filters, and reply to or forward messages. Use for building email agents that read and respond to incoming email.