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 mussolene/1c_hbk_bsl --skill oacs_codex_runtimegit clone --depth 1 https://github.com/mussolene/1c_hbk_bslWrote 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/mussolene/1c_hbk_bsl/oacs_codex_runtime)<a href="https://agentmods.dev/skills/mussolene/1c_hbk_bsl/oacs_codex_runtime"><img src="https://agentmods.dev/badge/skills/mussolene/1c_hbk_bsl/oacs_codex_runtime/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/mussolene/1c_hbk_bsl/oacs_codex_runtime"><img src="https://agentmods.dev/badge/skills/mussolene/1c_hbk_bsl/oacs_codex_runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.01814 |
| Opus 5 | $0.00032 | $0.00907 |
| Sonnet 5 | $0.00013 | $0.00363 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
codex-oacs-runtime 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 9d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex OACS Runtime
This is a non-standard optional implementation/dogfood layer. It combines the existing repo development memory adapter with an OACS-aware Codex runtime workflow. It shows how repository development memory can live as a removable skill layer without making Codex, Python, SQLite, or this workflow part of the OACS portable standard.
Treat Codex chat history as a cache. Treat repository files, git state, OACS
evidence, OACS memory, OACS audit, and OACS checkpoints as the source of truth.
OACS is the standard/contract layer; Python acs CLI/API/SQLite behavior is a
reference implementation and must not be described as the standard itself.
Script Actions
The skill.json entrypoint keeps the repo-local script adapter:
context: build a repo-scoped Context Capsule.capture: commit a manual D1 repository episode.auto_start: build context and audit metadata without writing memory.auto_finish: commit a D1 repository episode for the completed iteration.autorun: build context, run a bounded local command, and commit a D1 repository episode with command outcome metadata.
Policy:
- Auto mode commits only D1
episodememory. - D2 facts, D2 procedures, rules, and D3-D5 patterns require explicit review
through
memory propose,memory commit, andmemory sharpen. - Standalone tool-result evidence does not enter context by itself; attach the evidence ref to reviewed memory if it should guide future context builds.
- Preserve attribution when distilling memory: user instructions, agent decisions, tool observations, project policies, and human approvals are different roles in the standard and should not be collapsed into plain text.
- In strict policy mode, the actor running this skill needs ordinary
context.build,context.explain, memory, evidence, checkpoint, and audit grants; the skill must not rely onsystembootstrap authority.
Start or Resume
At the start of substantial work, choose or derive a stable task id. Reuse that same task id after compaction or in a new chat. If the task id is unknown, list recent checkpoints and ask the user or infer from current repo/user context before resuming.
What ships with it
2 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.
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.
- 9d ago First seen · 216 lines · 0 tokens per session scan A 8d50a41c2dc1
codex-oacs-runtime is a skill published in the GitHub repository mussolene/1c_hbk_bsl (9 stars, last pushed 14d ago), licensed MIT. It adds 63 tokens to every session and 1,814 once invoked, about $0.0003 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
bsp
A guide for developing and reviewing business software in 1C with its Standard Subsystems Library, a collection of shared building blocks for common tasks.
docx-from-sample
A document-building tool that creates a new DOCX file using an existing DOCX as its formatting template. DOCX is the file format used by Microsoft Word.
1c-bsp-registration
A helper for 1C external reports and processors that adds the function needed to register them in the Standard Subsystems Library (БСП). БСП is a set of reusable features for 1C configurations.
claude-md-bootstrap
A project setup tool that creates or updates a CLAUDE.md file, which gives an AI coding agent project-specific instructions and background at the start of each session.
1c-cfe-patch-method
A tool for creating method interceptors in a 1C configuration extension. 1C is business software, and an interceptor can run code before, after, or instead of an inherited method.
v8unpack-cf
A Python tool for unpacking and rebuilding 1C configuration files (CF, CFE, and EPF) as readable JSON and BSL source files. 1C is a business software platform widely used in Russian-speaking companies.