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/conectlens/lenserfight/smart-commitnpx skills add conectlens/lenserfight --skill smart-commitgit clone --depth 1 https://github.com/conectlens/lenserfightWhat 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 | $0.00073 | $0.01664 |
| Opus 5 | $0.00036 | $0.00832 |
| Sonnet 5 | $0.00015 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00166 |
Grade A, and why
smart-commit 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Commit
Inspect the working tree, classify every change first, group into logical commits, then handle each commit separately with explicit user approval.
Never commit without user confirmation. Never lump unrelated changes into one commit.
Workflow
Step 1 — Snapshot the working tree
Run all three commands and keep the output in context:
git status --short
git diff --stat HEAD
git diff --cached --stat
If both staged and unstaged areas are empty, tell the user there is nothing to commit and stop.
Step 2 — Read the full diff
# Staged changes
git diff --cached
# Unstaged changes
git diff
Skim hunks to understand what changed, not just which files. Treat both staged and unstaged as candidates — classification covers everything.
Step 3 — Classify ALL changes (REQUIRED FIRST STEP)
This step is mandatory before any staging or committing decision is made.
Map every changed file (staged or unstaged) to a conventional-commit type:
| Type | When to use |
|---|---|
feat |
New user-visible feature or capability |
fix |
Bug fix or incorrect behavior corrected |
refactor |
Code restructuring with no behavior change |
perf |
Performance improvement |
test |
Adding or updating tests only |
docs |
Documentation, comments, README only |
style |
Formatting, whitespace, lint — no logic change |
chore |
Build scripts, deps, tooling, config |
ci |
CI/CD pipeline changes |
revert |
Reverts a previous commit |
Output a classification table immediately:
| File | Status | Type | Scope | Brief description |
|---|---|---|---|---|
path/to/file.ts |
staged/unstaged | feat |
auth |
Added login form |
path/to/other.ts |
unstaged | chore |
deps |
Updated lockfile |
Do not proceed to Step 4 until this table is shown to the user.
Step 4 — Group into logical commit units
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 · 187 lines · 73 tokens per session scan A 6db1fd3d646e
smart-commit is a skill published in the GitHub repository conectlens/lenserfight (19 stars, last pushed 22d ago), licensed MIT. It adds 73 tokens to every session and 1,664 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
api-security-testing
Security-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object…
fix-security-vulnerabilities-with-strix
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use…
owasp-top-10-testing
Test an application against the OWASP Top 10 with Strix — autonomous AI agents that attempt real exploits for each category of the current OWASP Top 10:2025 (broken access control including SSRF, security misconfiguration, software supply chain failures, cryptographic failures, injection, insecure design…
find-security-vulnerabilities-in-code
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy…
web-app-penetration-testing
Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature…
application-security-testing
Application security testing (AppSec) across a whole product with Strix — decide which asset needs which test (source code, running web app, API, CI pipeline), run it, and turn the results into a ranked remediation plan. Autonomous agents exploit and prove each issue instead of emitting static-analysis alerts, so the…