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 opencue/cuecards --skill codebase-documentergit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/codebase-documenter)<a href="https://agentmods.dev/skills/opencue/cuecards/codebase-documenter"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/codebase-documenter/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/opencue/cuecards/codebase-documenter"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/codebase-documenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 79 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 60 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00123 | $0.03393 |
| Opus 5.5 | $0.00049 | $0.01357 |
| Sonnet 5.5 | $0.00025 | $0.00679 |
| Haiku 4.5 | $0.00012 | $0.00339 |
Grade A, and why
codebase-documenter 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 1mo 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Documenter
Generate developer-facing documentation that helps new team members become productive quickly.
Produces a single docs/CODEBASE.md with architecture diagrams, component descriptions,
data flow, setup instructions, and an onboarding reading path.
The Inclusion Test
Before writing any line, ask: "Would a new developer need to know this to become productive?"
- If yes → include it
- If no → cut it
Dense, specific content beats comprehensive coverage. Every section should earn its place.
Source of Truth: Code First
The codebase is the primary source of truth — not the README, not the wiki, not inline comments. Repository documentation (README.md, ARCHITECTURE.md, CONTRIBUTING.md) is frequently outdated: it describes what the project was, not what it is.
When exploring, always prioritize reading actual code over reading documentation:
- Derive architecture from imports, entry points, and module structure — not from what the README claims the architecture is
- Extract commands from Makefile, package.json scripts, CI config — not from README setup instructions that may be stale
- Identify patterns from how the code actually works — not from design docs that may describe aspirational patterns never implemented
- Get version numbers from dependency files — not from docs that forget to update them
When documentation and code disagree, trust the code. Note the discrepancy if relevant ("README says X, but the code actually does Y") but document reality.
Documentation is still useful for context that code can't express: the why behind decisions, domain terminology, and business rules. Read it — but verify against code before including any claim in the output.
Constraints
- Only describe what can be inferred from actual code, config, and git history
- Never invent undocumented behavior or hypothetical scenarios
- All file paths must point to files that exist
- All version numbers must come from dependency files, not from memory
- All commands must be real — extracted from Makefile, package.json, CI config — verified to actually exist, not copied from README without checking
- Complement existing docs (README.md, AGENTS.md), don't duplicate them
What ships with it
7 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.
- 1mo ago First seen · 321 lines · 123 tokens per session scan A e196589ad413
codebase-documenter is a skill published in the GitHub repository opencue/cuecards (6 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 3,393 once invoked, about $0.0005 per session on Opus 5.5. 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
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.
loongsuite-pilot-ops
Skill "loongsuite-pilot-ops" from alibaba/loongsuite-pilot, covering loongsuite-pilot-ops, quick start, todo: add quick start commands and usage.
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…
sipcode-regress
Check the user's own local Claude Code and Codex logs for regressions after an update (prompt-cache misses, 5-minute cache TTL, uncached context, hourly cache rebuilds, Codex usage limit draining faster per token) and pin each one to the version that introduced it, using the Sipcode CLI. Use when the user asks whether…
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.