Install
$ agentstack add skill-niftymonkey-skills-fork ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
> Adapted from mattpocock/skills, MIT License (LICENSE). Source: skills/productivity/handoff.
Write a handoff document that branches a single task off the current conversation, so a separate agent can run it independently while this conversation stays focused on its own work. Save it to ./fork-.md in the working directory, where ` is a short kebab-case label for the task. The file is personal session state: if fork-*.md is not already gitignored, add it to .git/info/exclude`.
Carry forward everything the forked task needs, and nothing else. The filter is relevance to the fork's stated purpose, not recency in the conversation; what passes travels verbatim, not summarized. Make sure the document carries each of these that exists:
- The task. What the forked session must do, the realization that surfaced it, and anything about it still unresolved.
- Why it surfaced. The connection in the current work that made this task necessary. This is the single most perishable thing in the document: the current session knows it, a cold agent cannot reconstruct it.
- Hard-won understanding. Research findings, with sources and exact specifics; and the connections the conversation worked out between modules, systems, or pieces of context. These are the costliest things for a cold agent to rederive, so they go in full, never as a pointer to "we figured something out".
- What's already settled. Decisions and constraints the forked task must respect, and approaches already ruled out, with the reason.
- Orientation. Where to start in the repo: the relevant files, modules, and docs.
Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
The document is single-use: delete it once the forked agent has picked up the task.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: niftymonkey
- Source: niftymonkey/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.