Install
$ agentstack add skill-llawliet11-claude-skills-toolkit-nf-direnv ✓ 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
nf-direnv
Set up .envrc in the current git repo with GH_TOKEN derived from a chosen gh account. The token stays dynamic — no plaintext in the file, rotation is automatic.
Workflow
- Check + list accounts — run
scripts/setup.sh check. Returns JSON{direnv, git, accounts, default, remote}.
direnv: false→ STOP. Tell userbrew install direnv.git: false→ STOP. Skill needs a git repo.accounts: []→ STOP. Tell usergh auth loginfirst.
- Pick account — present
accountsvia AskUserQuestion. Pre-selectdefault(script infers it from remote owner; empty string means no confident default — make the user choose).
- Preview — run
scripts/setup.sh preview. Show output verbatim (BEFORE / AFTER / DIFF). Ask user to confirm before writing.
- Apply — on confirm, run
scripts/setup.sh apply. Script writes.envrc, runsdirenv allow, and ensures.envrcis in.gitignore.
- Commit
.gitignore— if the script reported it added.envrc, ask user to commit per your project's git conventions (branch check, ticket ID, prefix). NEVER commit.envrcitself.
Account → owner mapping
scripts/setup.sh maps git-remote owner → default account:
| Owner pattern | Account | |---|---| | acme*, Acme* | acme-bot | | widgetco*, WidgetCo* | widgetco-bot | | my-personal-account or no remote | my-personal-account | | (unknown) | empty — user must pick |
Edit infer_default in scripts/setup.sh when adding a new account or org.
Rules
- NEVER hardcode tokens. The script always emits
$(gh auth token --user ...)so direnv resolves at load time. - NEVER proceed past steps 2 and 3 without explicit user confirmation.
.envrcMUST stay gitignored — per-developer config; account choice varies per machine.- If
gh auth tokenfails when direnv loads, user runsgh auth loginthendirenv reload.
Resources
scripts/setup.sh— orchestrator with subcommandscheck|preview|apply. Handles preflight, account inference, in-place GH_TOKEN replacement, idempotent.gitignore.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: llawliet11
- Source: llawliet11/claude-skills-toolkit
- 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.