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/ourines/codes/codes-e2e-testnpx skills add ourines/codes --skill codes-e2e-testgit clone --depth 1 https://github.com/ourines/codesWhat 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 | $0.00047 | $0.05831 |
| Opus 5 | $0.00023 | $0.02916 |
| Sonnet 5 | $0.00009 | $0.01166 |
| Haiku 4.5 | $0.00005 | $0.00583 |
Grade E, and why
codes-e2e-test scanned grade E with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST -H "Authorization: Bearer $TOKEN" -d '{"text":"test"}' "$BASE/dispatch") Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "$BASE/health" | python3 -c "import json,sys; d=json.load(sys.stdin); assert d['status']=='ok'; print('PASS')" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TEST_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$BASE/health" | python3 -c "import json,sys; d=json.load(sys.stdin); assert d['status']=='ok'; print('PASS')" How it starts
The opening of the file, as written. The whole thing — 927 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codes E2E Test Suite
codes CLI 全功能端到端验证。每个模块遵循 Setup → Execute → Assert → Cleanup 模式。
Test Modes
| Mode | Purpose |
|---|---|
--all |
Run all modules (1-10) |
--module <name> |
Run single module: project, profile, config, remote, agent, workflow, mcp, cli, http, notify |
--issue <number> |
Run issue-specific verification (Module 11) |
--quick |
Modules 1, 3, 8 only (Project + Config + CLI basics) |
Prerequisites
cd /Users/ourines/Projects/codes
go build -o /tmp/codes-e2e-bin ./cmd/codes
Verify: /tmp/codes-e2e-bin version should output version info.
Set test binary alias for all subsequent steps:
CODES="/tmp/codes-e2e-bin"
Module 1: Project CRUD
TEST_DIR=$(mktemp -d /tmp/codes-e2e-project-XXXXXX)
mkdir -p "$TEST_DIR"
$CODES project add e2e-test-proj "$TEST_DIR"
Assert: Output contains success message. Exit code 0.
$CODES project list
Assert: Output contains e2e-test-proj and the path $TEST_DIR.
$CODES project list --json
Assert: Valid JSON output. Contains key e2e-test-proj.
$CODES --json project list 2>/dev/null | grep -q "e2e-test-proj"
Assert: Project info is retrievable.
$CODES project remove e2e-test-proj
Assert: Exit code 0. $CODES project list no longer shows e2e-test-proj.
rm -rf "$TEST_DIR"
Module 2: Profile CRUD
Note: profile add and profile select are interactive (TTY) commands. This module tests them
via direct config file manipulation as a fallback, or requires manual interaction in a TTY session.
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 · 927 lines · 47 tokens per session scan E fc03612a7cfa
codes-e2e-test is a skill published in the GitHub repository ourines/codes (11 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 5,831 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it E with 4 findings (sends data to an external url, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-rig-awareness
Understanding claude-rig — a tool that manages multiple Claude Code configurations ("rigs") in parallel. MUST be consulted before modifying any Claude Code configuration: installing/removing plugins, adding/configuring MCP servers, editing settings.json, editing .claude.json, editing CLAUDE.md, adding skills, hooks…
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
format-specific-extraction
Format-specific document extraction workflows.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
api-server-mcp
REST API server and MCP protocol integration.