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/b3rys/b3rys-team-osnpx agentmods add skills/b3rys/b3rys-team-os/b3os-ai-code-safetyWrote 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/b3rys/b3rys-team-os/b3os-ai-code-safety)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-ai-code-safety"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-ai-code-safety/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/b3rys/b3rys-team-os/b3os-ai-code-safety"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-ai-code-safety.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 | $0.00124 | $0.04998 |
| Opus 5 | $0.00062 | $0.02499 |
| Sonnet 5 | $0.00025 | $0.01000 |
| Haiku 4.5 | $0.00012 | $0.00500 |
Grade A, and why
b3os-ai-code-safety scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return fetch(config.apiUrl, { headers: { token: config.token } }); How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3rys AI Code Safety — Structure & Refactoring
As code and logic grow, the cost is not the happy path — it is coupling: a change ripples into places you did not touch, and a "small fix" breaks something unrelated. This skill is a code-structure and refactoring guide: structure well from the initial design so a change stays local, apply operational safety where effects live, and refactor deliberately when the code smells. (Team-workflow rules — backup-first, verbatim user input, don't-touch-working-logic — live in TEAM-OS, not here.)
Two throughlines:
- Structure to reduce side effects and coupling — so most changes stay in one place.
- Refactor when it smells — the "I fixed one thing and something unrelated broke" signal is coupling telling you where the structure is wrong.
Phase 1 — Design (structure before writing)
- Data flow / source of truth first. Map read → transform → write, and name the single source of truth for each piece of state. Confirm you read the live source, not a synced mirror that drops fields. (Root of the 2026-07-06 dashboard bug: a read hit the DB-synced registry, which lacked the
purposefield, instead ofagents.jsonwhere it lives — the code compiled and passed units, the output was wrong.) - SOLID as coupling design, not class patterns. (SOLID = five object-oriented design principles; here we use them as a low-coupling lens, not a class-pattern checklist.) Dependencies point inward — domain/use-case logic does not depend on framework/ORM/HTTP/infra (DIP, dependency inversion: depend on an abstraction, not a concrete infra type). One reason to change per module (SRP, single responsibility). Depend on the small slice you actually use (ISP, interface segregation: small interfaces). Add an abstraction only when a real extension axis exists (skip speculative OCP, open/closed).
- Module boundaries hide volatile decisions. A module's public contract is a schema/interface/event/API; its private choices (storage, format, algorithm) stay hidden and swappable. One owner per concern — no two modules writing the same mutable state.
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.
- 10d ago First seen · 315 lines · 124 tokens per session scan A 6d69eaf5fdfb
b3os-ai-code-safety is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 4,998 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
dos-unstick
Analyze BLOCKED/DRAIN run history, cluster recurring causes, and propose one structural fix per wedge via dos decisions. Use when a fleet keeps stalling and you want a systemic unblock rather than another manual nudge.
cordis-plugin-sofagent-rollback
A sofagent plugin for undoing changes in reverse order after an error, using Git snapshots and cleanup handlers for registered effects.
log-troubleshooting
Investigate and troubleshoot daemon logs at /.comis/logs/. Covers NDJSON log format, Pino level codes, field dictionary, and staged analysis strategies for efficient troubleshooting of large log files. Use this skill whenever the user asks about logs, errors, warnings, daemon issues, slow operations, debugging daemon…
refire
Turns confirmed findings from a taste into one scoped fix run, then re-verifies each finding at its cited location. Use after /sous-chef:taste when the user says to fix the findings, apply the review, or refire it. Not for new feature work - that is a fresh /sous-chef:fire.
fable-commander
A planning and review workflow in which one model prepares decisions while selected models handle research and execution. It is written for Fable and Claude Code, tools for coordinating multi-step software work.