A security-focused coding guide for AI agents that emphasizes avoiding common software weaknesses.

Writing, reviewing, or modifying code with secure defaults and attention to common vulnerabilities.

It helps catch security problems while code is being written, reviewed, or changed, rather than relying only on later checks.

codeguard — Skill by cosai-oasis

Install

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.

agentmods

npx agentmods add skills/cosai-oasis/project-codeguard/codeguard

Any agent

npx skills add cosai-oasis/project-codeguard --skill codeguard

Clone the repo

git clone --depth 1 https://github.com/cosai-oasis/project-codeguard

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,366 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin unknown 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	$0.00041	$0.02366
Opus 5	$0.00020	$0.01183
Sonnet 5	$0.00008	$0.00473
Haiku 4.5	$0.00004	$0.00237

Measured yesterday against content hash 53ca1201f3fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codeguard 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 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.

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.

skills/codeguard/SKILL.md · 103 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

What ships with it

23 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.

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.

yesterday First seen · 103 lines · 41 tokens per session scan A 53ca1201f3fe

Subscribe to this mod's changes

codeguard is a skill published in the GitHub repository cosai-oasis/project-codeguard (326 stars, last pushed 3d ago), with no licence file. It adds 41 tokens to every session and 2,366 once invoked, about $0.0002 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 2026-08-30.

Security Writing and docs agentic-ai agents ai ai-generated-code coding cybersecurity

remind-capture

Write durable memories to Remind while working. Use when a decision is made, an approach succeeds or fails (outcome), the user states a preference or corrects you, a concrete fact surfaces (config value, name, date, owner), or an open question is raised.

sandst1/remind · 61 tokens

remind-curate

Maintain Remind memory quality. Use when recall output shows an OPEN CONFLICTS warning, the user corrects previously stored information, stored memories are outdated or misfiled, labels need reorganizing, a work session is wrapping up, or after ingesting multiple documents from different sources or time periods. This…

sandst1/remind · 81 tokens

remind-context

Retrieve context from Remind memory before acting. Use at session start, before answering questions about prior decisions, preferences, or project history, when starting work on a familiar file/area, or when asked "what do we know about X" or "what did we believe at time T".

sandst1/remind · 62 tokens

codeguard