A repository setup command that installs a Git commit-checking boundary. Git is the version-control system used to track code changes.

Use it to enroll a repository, install its verifier and receipt runtime, create its metadata directory, and show manual integration instructions when needed.

It makes the repository's checking hook available while avoiding replacement of an unrelated existing hook and stopping when setup is blocked.

oc-enroll — Command for Claude Code by asfbay-bit/opchain-skills

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add asfbay-bit/opchain-skills

Claude Code

/plugin install opchain

Made for: Claude Code.

Or install opchain, the plugin that ships this one along with the rest of its 36 skills, 16 commands, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/asfbay-bit/opchain-skills/oc-enroll/github.svg)](https://agentmods.dev/commands/asfbay-bit/opchain-skills/oc-enroll)

Your own site

<a href="https://agentmods.dev/commands/asfbay-bit/opchain-skills/oc-enroll"><img src="https://agentmods.dev/badge/commands/asfbay-bit/opchain-skills/oc-enroll/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/asfbay-bit/opchain-skills/oc-enroll"><img src="https://agentmods.dev/badge/commands/asfbay-bit/opchain-skills/oc-enroll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 684 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00011	$0.00684
Opus 5.5	$0.00004	$0.00274
Sonnet 5.5	$0.00002	$0.00137
Haiku 4.5	$0.00001	$0.00068

Measured 2d ago against content hash 50d8d562b5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oc-enroll 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 2d 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.

plugins/opchain/commands/oc-enroll.md · 49 lines

What it actually says

Implements the oc-bug-check enrollment contract. This is repository setup, not a next-skill handoff. Installing the plugin installs no gate: until this command succeeds, no hook checks anything in this repository. Resolve the current repository root, then run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/install-git-drivers.mjs" --enroll --repo "$(git rev-parse --show-toplevel)"

This explicit enrollment copies the packaged verifier and receipt runtime beneath the repository's Git common directory, installs three managed hooks, and creates .opchain/ only after setup succeeds:

pre-commit — reruns the declared checks on the exact staged candidate and writes the receipt that is the final commit decision.
post-commit — runs even under --no-verify. When HEAD's tree has no PASS receipt it writes .git/opchain/bypasses/v1/<sha>.json, appends to the bug-check checkpoint's skill_state.bypasses, and prints a warning. The reason comes from the commit's Opchain-Bypass: trailer.
pre-push — refuses to push any commit that has neither a PASS receipt nor an Opchain-Bypass: trailer, listing the commits. Commits a rebase or cherry-pick rewrote are excused. OPCHAIN_PUSH_BYPASS=1 git push is the loud escape hatch; use it once for history that predates enrollment.

If setup exits nonzero or prints BLOCKED, stop. Never overwrite an existing foreign hook. Show the user the exact manual integration snippet emitted by the installer and do not claim commit enforcement until their hook manager runs it.

Other modes, with the user's arguments in $ARGUMENTS:

--doctor — installs nothing. Prints PASS/FAIL per item: enrollment, runtime, each hook, the .bugcheck.json verification block, whether every declared command resolves (node_modules/.bin or PATH, npm run scripts exist), and whether node_modules/ is a real install rather than a .vite-only cache. Run it when a gate FAILs with exit 127 or on a fresh worktree.
--ci [--force] — enrolls, vendors the verifier into .opchain/runtime/, and writes .github/workflows/opchain-evidence.yml so every pull request runs verify-candidate run and the evidence:pr gate without the plugin. Never overwrites an existing workflow without --force. Tell the user to commit both.
--claude-md — creates or updates the managed opchain section of CLAUDE.md naming this repository's verbs (/oc-commit, /oc-pr or /oc-git-sync, /oc-deploy, /oc-bugcheck, /oc-enroll) and the rule that commits go through the gate, PRs carry the docs packet, and --no-verify never happens without /oc-bugcheck bypass.

Changes

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.

2d ago Changed · +30 lines 50d8d562b5f0
1mo ago First seen · 19 lines · 11 tokens per session scan A 87a4bd201441

Subscribe to this mod's changes

oc-enroll is a command published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 684 once invoked, about $0.0000 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 2026-09-14.

Commits Git and workflow

oc-enroll

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

standup

git

session-report

commit

git-workflow

commit