Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/bunhine0452/ocul-pm/oculpm-codex)<a href="https://agentmods.dev/skills/bunhine0452/ocul-pm/oculpm-codex"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/oculpm-codex/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/bunhine0452/ocul-pm/oculpm-codex"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/oculpm-codex.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 | $0.00381 |
| Opus 5 | $0.00013 | $0.00191 |
| Sonnet 5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade B, and why
oculpm-codex scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Register the MCP server through ocul-pm Settings → Integration → Codex MCP server. It writes one entry in Codex's `config.toml` and never touches Claude settings. The entry carries no `--root`: `~/.codex/config.toml` i What it actually says
ocul-pm for Codex
Use this skill in a project that has .oculpm/.
- Prefer the
oculpmMCP tools when they are available. - If no MCP tools are available, follow the repository's
AGENTS.mdjournal and planner rules directly. - Register the MCP server through ocul-pm Settings → Integration → Codex MCP server. It writes one entry in Codex's
config.tomland never touches Claude settings. The entry carries no--root:~/.codex/config.tomlis machine-wide, so the project is decided by the folder the session opened in. Never add--rootthere by hand — a pinned root sends journals from every other project to that one path. - Do not use Claude-specific variables such as
CLAUDE_PLUGIN_ROOTorCLAUDE_PROJECT_DIRin Codex configuration. - When Claude Code is also installed, leave its plugin, hooks, and
.mcp.jsonregistration independent. Both agents may use the same.oculpm/journal and planner files. - This plugin ships hooks in
hooks/hooks.json, not as a manifest field: Codex rejects ahooksfield in a marketplace plugin manifest but reads that file by convention. Session markers, the journal delivery gate, and the plan-context injection all come from it, and the scripts resolve the project from the hook payload'scwdrather thanCLAUDE_PROJECT_DIR. - Codex asks once whether to trust a plugin's hooks. Decline it and the plugin still works as skills, but session markers and the delivery gate stay silent — nothing else reports that, so answer the prompt deliberately.
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.
- yesterday Changed · +1 lines a80a35f6823a
- 4d ago Changed · +1 lines 091c9f88cb78
- 5d ago First seen · 15 lines · 26 tokens per session scan B c992ab8d588a
oculpm-codex is a skill published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 381 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
linear
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
product-strategy
A product-planning guide for evaluating requirements, users, scope, priorities, roadmaps, and success measures. It ties proposals to user problems, business value, boundaries, and signals that can be checked.
pm-long-horizon-planning
Audit long, complex, and potentially inconsistent PM taskbooks and compile them into one self-contained, semantically validated Product Brief with a requirement ledger, WP dependency graph, budgets, absolute schedule, gates, tests, experiment evidence, risks, recovery, and stop conditions. Use for long-horizon or…
pm-product-requirements
Turn vague ADMIN requests, chat feedback, screenshots, and workflow complaints into scoped CodeFlowMu product requirements. Use when PM needs PRD-style clarification, user stories, goals, non-goals, constraints, risks, or task input while preserving FCoP boundaries.
pm-acceptance-criteria
Convert "done" into checkable CodeFlowMu acceptance criteria. Use before PM dispatch, PM review, QA verification, or ADMIN closure to define functional, file, behavior, evidence, and forbidden-item checks.