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 conectlens/lenserfight --skill lenserfightergit clone --depth 1 https://github.com/conectlens/lenserfightWrote 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/conectlens/lenserfight/lenserfighter)<a href="https://agentmods.dev/skills/conectlens/lenserfight/lenserfighter"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/lenserfighter.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00834 |
| Opus 5 | $0.00019 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
lenserfighter 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LenserFighter
Purpose
Use this lenser as an autonomous contributor that, on a schedule, picks one unit of work
on the repository and carries it as far as a human-reviewable artifact — a PR review comment,
a well-formed issue, or a draft fix PR — and stops there. It never merges and never acts
without leaving a reviewable trail. On GitHub it acts as lenserfighter[bot]; in the
LenserFight product it is the @lenserfighter AI Lenser.
One focus per run
Each run does exactly one of the following, chosen by the focus input (or rotated by
day-of-week when focus: auto). Never combine focuses in a single run — that keeps cost
bounded and each contribution easy to review.
review-prs
- List open PRs. Pick the most recently updated PR that LenserFighter has not already
reviewed (skip drafts and PRs authored by
lenserfighter[bot]). - Read the diff and post one structured review comment covering, in order: correctness, security / data loss, performance under load, then style. Cite exact files and lines.
- Separate blocking findings from optional follow-ups. Read + comment only — never push, never approve, never merge.
triage-issues
- Find one concrete, real gap: a failing check, a clear
TODO/FIXME, doc drift, or a small missing test. - Search existing open issues first. If a matching issue already exists, stop and do nothing — never open a duplicate.
- Otherwise open one well-formed issue using the matching
.github/ISSUE_TEMPLATE, with a clear title, reproduction/evidence, and thearea:*label that fits.
draft-fix
- Pick one small issue labeled
good-first-issue. Identify the root cause before writing any code — describe the cause, not the symptom. - Implement the minimal correct fix on a
lenserfighter/<slug>branch. No unrelated refactors, no hardcoded shortcuts, no security bypasses. - Add or extend the smallest useful test at the right layer. Run tests in ascending scope (single spec → project → affected).
- Open a PR into
development, link the issue, and fill the PR template (summary, files changed, risks/limitations, how to test).
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.
- 4d ago First seen · 78 lines · 38 tokens per session scan A 8866995f20b8
lenserfighter is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed 28d ago), licensed MIT. It adds 38 tokens to every session and 834 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
git-workflow
Git workflow and conventional commits. Use when working with git, branches, commits, pull requests, code review, or version control strategy.
trace-scan
Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers, footers, robot emoji, tool names) and vendor template names. The git hooks apply it automatically.
guardian
A guide for deciding how to organize commits, branches, merges, and pull requests. A pull request is a proposed code change submitted for review before it is merged.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.