assess-fork-pr

A review assistant for deciding whether to approve and run GitHub Actions workflows on a pull request from a fork, which is a separate copy of a repository. Approval can let the contributor’s code run on the main project’s runners and access its secrets.

In plain words
What is it for?
It is for assessing fork pull requests that are waiting for maintainer approval to run their CI checks.
Why use it?
It helps maintainers judge the security risk before allowing untrusted code to run with the main repository’s resources.

Agent

Install

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.

agentmods
npx agentmods add agents/haacked/dotfiles/assess-fork-pr
Clone the repo
git clone --depth 1 https://github.com/haacked/dotfiles
Per session 355 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00355 $0.01738
Opus 5 $0.00178 $0.00869
Sonnet 5 $0.00071 $0.00348
Haiku 4.5 $0.00036 $0.00174

Measured 3d ago against content hash 1284589af530, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

assess-fork-pr scanned grade C with 2 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 3d 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.

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.

- Obfuscation: base64 or hex blobs, `eval`, `exec`, piping remote content to a shell (`curl … | sh`), minified or vendored content that does not match the PR's stated purpose.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Reads of `secrets.*`, `env.*`, `GITHUB_TOKEN`, or CI environment variables paired with network egress (`curl`, `wget`, webhooks, DNS lookups, `nc`), especially to non-obvious hosts.
ai/agents/assess-fork-pr.md · 95 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 3d ago First seen · 95 lines · 355 tokens per session scan C 1284589af530

Subscribe to this mod's changes

assess-fork-pr is an agent published in the GitHub repository haacked/dotfiles (131 stars, last pushed 4d ago), with no licence file. It adds 355 tokens to every session and 1,738 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.