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 TonyCasey/lisa --skill prgit clone --depth 1 https://github.com/TonyCasey/lisaWrote 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/tonycasey/lisa/pr)<a href="https://agentmods.dev/skills/tonycasey/lisa/pr"><img src="https://agentmods.dev/badge/skills/tonycasey/lisa/pr/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/tonycasey/lisa/pr"><img src="https://agentmods.dev/badge/skills/tonycasey/lisa/pr.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 | $0.00074 | $0.03546 |
| Opus 5.5 | $0.00030 | $0.01418 |
| Sonnet 5.5 | $0.00015 | $0.00709 |
| Haiku 4.5 | $0.00007 | $0.00355 |
Grade A, and why
pr 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 1mo 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Model-neutral helper for GitHub PR workflow operations including creating PRs with auto-generated content, checking CI status, linking PRs to issues, polling for and addressing review comments, tracking PRs you're working on, and saving PR notes to memory.
Triggers
Use when the user says: "create pr", "pr create", "pr checks", "check pr", "pr link", "link pr", "link pr to issue", "pr poll", "poll pr", "pr address", "address comments", "pr comments", "view comments", "watch pr", "unwatch pr", "watching", "what prs am i watching", "pr status", "pr remember", "remember pr", "save pr note".
How to use
Create a PR
Create a PR with auto-generated body, issue linking, and auto-watch:
# Create PR from current branch (auto-detects base branch and linked issues)
lisa pr create
# Create PR linking to specific issues
lisa pr create --issue 40 --issue 41
# Create PR with custom title and base branch
lisa pr create --title "feat: add pr create command" --base develop
# Create as draft PR
lisa pr create --draft
# Skip auto-watching the PR
lisa pr create --no-watch
# Skip commenting on linked issues
lisa pr create --no-comment
# Output as JSON
lisa pr create --json
Features:
- Auto-detects linked issues from branch name (supports:
15,15-description,feature/15,issue-15,fix/#15) - Auto-generates PR body with Summary (from commits), Test Coverage (test files changed), and Linked Issues (
Closes #N) - Comments on linked issues with
PR: #N - Auto-watches the PR for future polling
- Creates Neo4j relationships (
CLOSES) between PR and issues
Output:
Created PR #51: https://github.com/owner/repo/pull/51
Linked issues: #40
Check PR CI Status
Get the current status of CI checks for a PR:
# Check current repo's PR
lisa pr checks <PR_NUMBER>
# Check specific repo's PR
lisa pr checks <PR_NUMBER> --repo owner/repo
# Output as JSON
lisa pr checks <PR_NUMBER> --json
Output:
PR #50 Checks
fix(github): prevent shell injection in GithubClient
✅ 2 passed, 0 failed
✓ ci/build
✓ security/gitguardian
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 520 lines · 74 tokens per session scan A 6a84a9015060
pr is a skill published in the GitHub repository TonyCasey/lisa (9 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 3,546 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…