Install
$ agentstack add skill-bnet47-codexicon-discover ✓ 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
Discover
Announce: "I'm using discover to define the project before we choose how to build it."
1. Check the gate
Inspect agent_docs/briefs/ and the identity section in AGENTS.md.
- If an approved project charter already exists, summarize it and ask whether the user wants to revise it. Do not create a duplicate.
- If this is an established repository with clear project identity, stop and route the request to the relevant feature workflow.
2. Build understanding
Ask one question at a time and stop as soon as the answer is clear. Keep the exchange focused on unresolved decisions.
Cover only unresolved parts of:
- What is painful, missing, or expensive today?
- Who experiences it, and what do they do now?
- What concrete change should the project create for that person?
- Why is this worth solving now?
- What constraints and existing systems are real?
- What is explicitly not part of the project?
Do not choose a language, framework, database, or deployment target in this workflow.
3. Reflect before writing
Return a two- or three-sentence synthesis of the problem, person, and intended outcome. Resolve material corrections before saving.
4. Write the charter
Save agent_docs/briefs/charter-[project-slug].md:
# Project Charter: [Project name]
**Date:** [YYYY-MM-DD]
**Status:** Approved
## Problem
[Pain, affected person, and current cost.]
## Intended user
[A specific person or role and their context.]
## Outcome
[The observable change when the project succeeds.]
## Why now
[Why the work matters now.]
## Constraints
- [Real limit or dependency.]
## Non-goals
- [Explicit boundary.]
## Success signals
- [Observable evidence without prescribing a feature.]
## Open questions
- [Unresolved item, or "None".]
Self-check that the charter describes a problem and outcome rather than a predetermined solution, and that non-goals are meaningful.
5. Hand off
Offer $init to configure the technical environment. Do not commit, push, or open a PR unless the user separately asks.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bnet47
- Source: bnet47/codexicon
- License: MIT
- Homepage: https://bnet47.github.io/codexicon/repo-template-playbook.html
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.