Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bnet47/codexiconnpx agentmods add skills/bnet47/codexicon/adopt-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/adopt-codexicon)<a href="https://agentmods.dev/skills/bnet47/codexicon/adopt-codexicon"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/adopt-codexicon/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/adopt-codexicon"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/adopt-codexicon.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 | $0.00028 | $0.00453 |
| Opus 5.5 | $0.00011 | $0.00181 |
| Sonnet 5.5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
adopt-codexicon 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 1mo 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
Adopt or update Codexicon
Use the repository-local manager from a trusted Codexicon source. Keep inspection read-only until the user explicitly authorizes apply.
1. Inspect
Confirm the intended source and target repository roots, then run:
python scripts/codexicon.py inspect TARGET
Report every create, identical, preserve, required-missing, and conflict result. Inspect existing project commands, AGENTS.md, .codex/, skills, CI, Git hooks, and project facts before recommending adoption. Do not treat a missing project-owned file as safe to synthesize automatically.
2. Adopt
Only after the user authorizes repository writes, run:
python scripts/codexicon.py adopt TARGET --apply
The manager copies only absent managed/merge files, preserves conflicts, records baseline hashes in .codexicon.lock.json, and returns nonzero while integration work remains. Resolve conflicts deliberately; never replace real project commands with template stubs.
After the user deliberately stages the adopted files, run python TARGET/scripts/codexicon.py sync-git-modes --root TARGET. It changes only manifest-declared executable bits on already-tracked index entries and refuses untracked paths; this is required for Windows-origin adoptions that will be cloned on POSIX.
Run python TARGET/scripts/codexicon.py doctor --root TARGET, then the target's canonical lint, test, and security commands.
3. Update
From an adopted target, inspect a trusted local release source before apply:
python scripts/codexicon.py update --root TARGET --source SOURCE
python scripts/codexicon.py update --root TARGET --source SOURCE --apply
Apply is explicit and offline. Unchanged baseline files may update or retire; locally modified files remain conflicts. Review changed hooks with /hooks because their trust hash changes.
Do not download releases, commit, push, publish, deploy, or modify external systems unless separately authorized.
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.
- 1mo ago First seen · 46 lines · 28 tokens per session scan A 52617207eabf
adopt-codexicon is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 453 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.