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 agentmods add skills/holetron-lab/fleet-memory/code-reviewnpx skills add Holetron-lab/fleet-memory --skill code-reviewgit clone --depth 1 https://github.com/Holetron-lab/fleet-memoryWhat 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 | $0.00035 | $0.02246 |
| Opus 5 | $0.00017 | $0.01123 |
| Sonnet 5 | $0.00007 | $0.00449 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
code-review 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review all changed code against the project's quality standards and coding conventions.
Code Standards
Read and internalize these standards before writing code. The review steps below verify compliance.
Python Style
- Python 3.11+, type hints required
- Async throughout (asyncpg, async FastAPI)
- Pydantic models for request/response
- Ruff for linting (line-length 120)
- No Python files at project root - maintain clean directory structure
- Never use multi-item tuple return values — not even for internal/private functions. Always use a dataclass or Pydantic model. No exceptions, no "it's just two values" shortcuts. If a function returns more than one value, define a named type for it.
Type Safety with Pydantic Models
NEVER use raw dict types for structured data — this applies to all code, including internal helpers and private functions. If the dict has known keys, it must be a dataclass or Pydantic model:
- Use Pydantic
BaseModelfor all data structures passed between functions - Use
@dataclassfor lightweight internal data containers when Pydantic validation isn't needed - Add
@field_validatorfor type coercion (e.g., ensuring datetimes are timezone-aware) - Avoid
dict.get()patterns - use typed model attributes instead - Parse external data (JSON, API responses) into Pydantic models at the boundary
- This catches type errors at parse time, not deep in business logic
- The only acceptable
dictusage is for truly dynamic/unknown keys (e.g., arbitrary metadata, JSON blobs with no fixed schema)
# BAD - error-prone dict access
def process(data: dict) -> str:
return data.get("name", "") # No validation, silent failures
# GOOD - typed and validated
class UserData(BaseModel):
name: str
created_at: datetime
@field_validator("created_at", mode="before")
@classmethod
def ensure_tz_aware(cls, v):
if isinstance(v, str):
v = datetime.fromisoformat(v.replace("Z", "+00:00"))
if v.tzinfo is None:
return v.replace(tzinfo=timezone.utc)
return v
def process(data: UserData) -> str:
return data.name # Type-safe, validated at construction
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 · 206 lines · 35 tokens per session scan A 18da725508bb
code-review is a skill published in the GitHub repository Holetron-lab/fleet-memory (0 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 2,246 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 2026-08-31.
Other skills, from other repositories
code-cleanup-audit
Audit a repository for architectural decay, AI-generated code smells, stale compatibility paths, dead abstractions, boundary violations, and cleanup candidates without modifying files. Use when the user asks to review code quality, find bad code, inspect AI-generated code, identify refactoring or cleanup…
author-pragma-dsl
Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation resources. Use when a user asks Pragma to create, change, configure, test, evaluate, or repair an Expert, team, Flow, Run Dry suite, schedule, trigger, or Automation in the current Pragma project.
claude-code-review
Delegate code review of current uncommitted repository changes to Claude Code with claude -p, wait up to 10 minutes, then independently verify each finding and fix real issues. Use when the user asks to have Claude Code review a diff, audit uncommitted changes, perform CR/code review, or turn Claude Code review…
portable-bundle-review
检查并解释 portable Pragma bundle 的内容、依赖和环境绑定。.
pragma-code-review
按正确性、架构边界、风险和验证四个维度审查代码。.
wolbarg-coordination
Coordinate with other Cursor agents via Wolbarg — but ONLY after wolbarg init. Brief the workspace, claim scopes, record findings/dead-ends, update work items, and hand off. Use when working in parallel with other agents, resuming prior agent work, avoiding duplicate exploration, or sharing decisions across sessions.