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 unkluco/line-locator --skill line-locatorgit clone --depth 1 https://github.com/unkluco/line-locatorWrote 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/unkluco/line-locator/line-locator)<a href="https://agentmods.dev/skills/unkluco/line-locator/line-locator"><img src="https://agentmods.dev/badge/skills/unkluco/line-locator/line-locator/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/unkluco/line-locator/line-locator"><img src="https://agentmods.dev/badge/skills/unkluco/line-locator/line-locator.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 | $0.00085 | $0.05430 |
| Opus 5 | $0.00043 | $0.02715 |
| Sonnet 5 | $0.00017 | $0.01086 |
| Haiku 4.5 | $0.00009 | $0.00543 |
Grade A, and why
line-locator scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
out = subprocess.check_output([...]) How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Line-Locator
Hai script phối hợp để định vị chính xác trước khi đọc:
| Script | Phạm vi | Câu hỏi trả lời |
|---|---|---|
findtree.py |
Cả cây thư mục | File nào chứa pattern này? |
findtool.py |
Một file duy nhất | Dòng nào trong file này? |
Workflow:
findtree.py (shortlist files) → findtool.py (locate lines) → view_range (read)
Script nằm tại: skills/line-locator/scripts/
Output contract
Tất cả pattern dùng Python regex.
findtool — success (stdout):
{"matches": {"processOrder": [247, 312]}}
{"line": 248}
{"matched": true}
findtree — success (stdout):
{"matched_files": ["src/order.js", "tests/order.test.js"]}
Failure — cả hai tool (stderr, exit 1):
{"ok": false, "error": "No line matching pattern 'foo' was found after line 0."}
Parse nhanh:
import json, subprocess
out = subprocess.check_output([...])
data = json.loads(out)
# findtool
lines = data["matches"]["pat"] # -mr → list[int]
line = data["line"] # -n / -b / -c / -o → int
matched = data["matched"] # -e → bool
# findtree
files = data["matched_files"] # list[str] relative paths
findtree — tìm file
python findtree.py --root ROOT --pattern PAT [options]
| Option | Mặc định | Mô tả |
|---|---|---|
--root |
(required) | Thư mục gốc |
--pattern |
(required) | Regex pattern |
--include GLOB... |
(tất cả) | Chỉ tìm file khớp glob |
--exclude GLOB... |
(không) | Bỏ qua file/thư mục khớp glob |
--ignore-case |
off | Case-insensitive |
--max-results N |
(không giới hạn) | Dừng sau N file |
--show |
matched |
matched / errors / both / summary / all |
--max-file-size |
(không) | Bỏ qua file lớn hơn (VD: 64K, 10M) |
--no-default-dir-excludes |
off | Tắt auto-skip .git, node_modules, v.v. |
--text |
off | Output text thay vì JSON |
Auto-excluded dirs: .git, .hg, node_modules, venv, .venv, __pycache__, dist, build, target, .mypy_cache, .pytest_cache, .tox, coverage
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.
- 9d ago First seen · 505 lines · 85 tokens per session scan A b76dd3b0aab2
line-locator is a skill published in the GitHub repository unkluco/line-locator (7 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 5,430 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wireshark-analysis
This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network…
argus
Argus — the all-seeing scanner suite. Six automated scanners for high-value web + LLM bug classes — CORS misconfiguration (origin reflection / null / credentialed read), CRLF & host-header injection, NoSQL injection (operator auth-bypass / $where blind), JWT attacks (alg:none / RS256→HS256 confusion / secret crack)…
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
octocode-research
Use when code must be checked, not assumed: trace connections (callers, imports, cross-repo wiring, what breaks if I change it), locate behavior, map a system, diagnose a failure, RCA. Also for external repositories, npm packages, upstream/prior art, and general research. Plan a coding flow before writing, validate it…
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
offensive-bug-identification
Systematic bug identification methodology: source code review patterns, black-box testing strategies, taint analysis, dangerous function hunting, data flow tracing, and automated scanning setup. Use for code audits, bug bounty triage, or building vulnerability identification pipelines.