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 bnet47/codexicon --skill reviewgit clone --depth 1 https://github.com/bnet47/codexiconWrote 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/bnet47/codexicon/review)<a href="https://agentmods.dev/skills/bnet47/codexicon/review"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/review/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/bnet47/codexicon/review"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/review.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 | $0.00029 | $0.00883 |
| Opus 5.5 | $0.00012 | $0.00353 |
| Sonnet 5.5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
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 24d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Review evidence, not intent. Do not modify files.
During Explore or Build, do not invoke Git. Review the changed paths recorded in TASKS.md against SPEC.md, acceptance criteria, and verification output. Git status, diffs, staging, and branch comparisons are reserved for $ship.
Selective independent review
Independent review is a configured Build decision, not a default panel or
runtime. The canonical $autonomous-build route delegates review when any
configured trigger matches; it must not narrow routing to risk alone. Before
deciding, validate and read the selected profile from
.codex/capabilities.toml with python scripts/codexicon.py capabilities --json; do not invent thresholds or substitute values from another profile.
Delegate the read-only reviewer profile when any configured trigger matches:
- the assessed task or change risk is in
required_risk_levels; - the changed-file count is greater than or equal to
changed_files_threshold; - the change has a public API, security, architecture, or test-complexity
signal and the corresponding
review_on_public_api,review_on_security,review_on_architecture, orreview_on_test_complexityflag is true.
The trigger is selective: trivial low-risk work is exempt when it is below the configured file threshold and none of the enabled signals is present. The primary agent remains the one sequential Build writer and still performs the normal self-review and focused checks. This is not a background runtime or an automatic publication mechanism. An independent review is exactly one read-only reviewer pass and one correction round; the reviewer may inspect files and evidence but must not edit, run publication, or expand Git, deployment, credential, external-write, or other Ship authority.
For a triggered review, completion evidence must carry a stable finding ID and
one disposition for every finding: accepted, fixed, rejected, or
not_applicable. Each finding gets exactly one of those dispositions. A
reviewer PASS has no actionable findings; it does not grant publication
authority or replace the task's required verification.
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.
- 24d ago Changed · +7 lines 6f8d238d619d
- 1mo ago Changed · +33 lines c73e9362c697
- 1mo ago Changed · +2 lines 766345899c4b
- 1mo ago First seen · 49 lines · 29 tokens per session scan A bd87428f8f61
review is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 20d ago), licensed MIT. It adds 29 tokens to every session and 883 once invoked, about $0.0001 per session on Opus 5.5. 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
review-team
Use when assigned a review or when an authored review boundary is reached.
receiving-code-review
Handle review feedback on code with care: understand each point, check it against the real code before changing anything, fix what is right, and push back with reasons on what is wrong. Use when review comments arrive.
oma-refactor
Restructure existing code while preserving observable behavior. Use for targeted technical debt or hotspot work with characterization tests.
address-pr-comments
Work through the review comments on a pull request: check each point against the code, make the changes that are right, answer the ones that are not, and hold every reply for approval before it is posted.
gentle-ai-judgment-day
Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
release
Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.