Borrowing it
Nothing to install: this file belongs to luthersystems/elps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/luthersystems/elps/main/.claude/skills/audit/SKILL.mdgit clone --depth 1 https://github.com/luthersystems/elpsWrote 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/luthersystems/elps/audit)<a href="https://agentmods.dev/skills/luthersystems/elps/audit"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/audit/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/luthersystems/elps/audit"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00996 |
| Opus 5.5 | $0.00000 | $0.00398 |
| Sonnet 5.5 | $0.00000 | $0.00199 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
audit 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 2d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit — Codebase Audit Skill
Performs a systematic, multi-category audit of the ELPS codebase.
Trigger
Use when asked to audit the codebase, find bugs, improve security, review code quality, or perform a comprehensive health check.
Workflow
1. Create Branch
git checkout main && git pull origin main
git checkout -b audit/<focus-or-date>
2. Scan Each Category
Work through categories systematically. For each finding: understand it, fix it, write a test if applicable, and commit as a logical unit.
Category 1: Bugs
Scan for:
- Returned
*LValerrors (LError) not checked and propagated - Walkers that treat values as trees: nested sharing (
(set! x (list x x))) makes them exponential (lisp/sharing.gohas the budget and memo pattern) - Builtins whose work grows with value size but charge no steps or skip
CheckAlloc
Where to look: lisp/, parser/, formatter/, lint/
Category 2: Security
Scan for:
- File access in builtins and the CLI: path traversal and symlink following (
os.Open,os.ReadFile,filepath.Walk) - Limits a program can bypass: the step budget,
MaxAlloc, and context cancellation
Run: make static-checks (gosec is enabled in .golangci.yml), make elpsvet (shared-state and native-payload invariants; /elpsvet), and a make fuzz pass over the packages in scope (/fuzz)
Where to look: lisp/lisplib/, cmd/, repl/
Category 3: Performance
Scan the eval loop and parser for allocations per call. Measure on the
whole-program benchmarks (BenchmarkWorkload) before and after, per the
/benchmark skill.
Where to look: lisp/env.go (eval loop), lisp/builtins.go, parser/rdparser/
Category 4: Tests
Scan for coverage gaps in error paths, and for tests that depend on shared state or wall-clock time.
Run: go test -cover ./... and examine coverage percentages.
Where to look: All _test.go files, compare against source files
Category 5: Documentation
Scan for:
- Missing docstrings:
./elps doc -m - Stale docs in
docs/lang.md(features added but docs not updated) - Incorrect help text (description doesn't match behavior)
- Missing examples in documentation
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.
- 2d ago First seen · 133 lines · 0 tokens per session scan A 423417bf87c9
audit is a skill published in the GitHub repository luthersystems/elps (36 stars, last pushed today), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 996 tokens. 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 2026-10-26.
Other skills, from other repositories
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
tui-render-debug
Diagnose and fix pi-go TUI rendering corruption, especially displaced panels, stale rows, cursor drift, and terminal-specific ANSI incompatibilities.
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.