skill-frane-agented-docs · by Install
$ agentstack add skill-frane-agented-docs ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-frane-agented-docs) 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
The skill
Run ae skill install once and a SKILL.md lands in every detected client's skills directory plus the canonical ~/.agents/skills/agented/. The default does the obvious thing: writes to ~/.agents/, ~/.claude/skills/, ~/.codex/skills/, and ~/.openclaw/workspace/skills/ if those clients are present (detected via home dir or binary on PATH).
ae skill install # write to every detected target
ae skill install --target claude # one target only
ae skill install --scope project # write inside the workspace instead of $HOME
ae skill install --dry-run # show what would happen
ae skill list # where it's installed and at what version
ae skill upgrade # re-install to the same set after a binary update
ae skill uninstall # remove only the agented/ subfolder, never sibling skillsTargets: agents, claude, codex, cursor, openclaw. Default --target all writes to every detected client.
What the skill teaches
The skill is half of why this works at all. It documents every verb in both forms, pairs every error with the recovery action, and walks through six full sessions covering the patterns that actually come up: read-modify-verify on a single function, a multi-file refactor that rolls back when the tests fail, backtracking after a wrong turn, and leaving a handoff for the next session.
Annotations
Worth their own section because most people miss them on first read. They're per-file notes the agent leaves for whoever opens the file next. ae open returns them inline, so the first thing any new session sees is what previous sessions thought was worth remembering. An agent's working memory is whatever fits in its context window, and that memory ends when the session ends. Annotations are how it persists across that gap.
ae an foo.go add -t "auth path is fragile, see commit 4f2a"
ae an foo.go list # also returned inline by ae open
ae an foo.go remove
ae an search "deprecated" # workspace-wide search across annotation bodiesSource & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: frane
- Source: frane/agented
- License: Apache-2.0
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.