adopt-ground
Brownfield grounding + safety pass: pack an existing repo into an AI-readable inventory (Repomix, token-budgeted), scan for secrets FIRST (Gitleaks/TruffleHog…
Skill by 6SNT-RADIO
Chalk Labs
Need help deploying adopt-ground?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/6snt-radio-adopt-ground
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adopt-ground
What's inside
- Skill name
adopt-ground- Description
- Brownfield grounding + safety pass: pack an existing repo into an AI-readable inventory (Repomix, token-budgeted), scan for secrets FIRST (Gitleaks/TruffleHog or a built-in heuristic), and audit dependencies/licenses — so reconstructed specs are grounded in real code, never in memory. Used by /adopt before any artifact is reconstructed.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# SKILL: adopt-ground — ground the codebase + safety, before reconstructing anything
Brownfield rule: never spec from memory. First produce a grounded INVENTORY of the real code, and screen for secrets BEFORE reading deep or generating docs. The output feeds 04/05/01/10 so their reconstructed artifacts reflect the actual system.
## Order (safety first)
1. **Secret scan FIRST.** Run `gitleaks detect` and `trufflehog filesystem .` (TruffleHog verifies if creds are still live) if installed. If not installed, run the built-in heuristic: grep high-signal patterns (`API_KEY`, `SECRET`, `TOKEN`, `PASSWORD=`, `BEGIN PRIVATE KEY`, `.env`, `github_pat_`, `sk-`, AWS `AKIA`) and list FILES + line numbers — NEVER the secret value. Any hit → STOP and escalate to the PO (P-02); quarantine before continuing.
2. **Inventory (grounding).** `npx repomix` → one AI-readable pack with per-file + total token counts. If it exceeds the working budget, use `--split-output` or restrict to the relevant subtree. Write a short `INVENTORY.md`: stack/languages, entry points, top dirs/modules, dependency list, token-size note. (Alternative for huge repos: an Aider-style symbol map; Repomix suffices under ~10k files.)
3. **Dependency & license audit.** `npm audit` / OSV / Snyk if available for known CVEs; list third-party licenses. Feed findings to 09 Security.
## Output
- `INVENTORY.md` (grounding doc for 04/05/01/10).
- Secret-scan result: PASS, or a list of `{file, line, pattern}` (no values) + PO escalation.
- Dependency/license notes.
## Environment note (P-06)
If Gitleaks/TruffleHog/Repomix aren't installed, the studio AUTHORS the exact commands and the PO/CI runs them (same pattern as `asset-sourcing`); the built-in heuristic is the always-available fallback so a secret scan ALWAYS happens. Never deliver "run the scan" as a silent skip.
## Anti-bloat
A grounding wrapper, not a platform. Local-first (Repomix, Gitleaks). No IDE/cloud lock-in. Reconstruction stays incremental + PO-reviewed (see `/adopt`).From 6SNT-RADIO/6SNT-Studio, MIT.
More from 6SNT-RADIO/6SNT-Studio
- 0.474score
research-methodology
6SNT-RADIO
For the Researcher (02).
SkillCFreshness: CClaude Code +9 - 0.474score
technical-documentation
6SNT-RADIO
For the Technical Writer (10).
SkillCFreshness: CClaude Code +9 - 0.474score
smoke-test
6SNT-RADIO
'Done' includes an artifact that STARTS: an automated headless smoke with ONE command, pass/fail by exit code, and tests/smoke-result.json for the…
SkillCFreshness: CClaude Code +9 - 0.474score
project-cleanup
6SNT-RADIO
For the Technical Writer (10).
SkillCFreshness: CClaude Code +9 - 0.474score
setup
6SNT-RADIO
Activates the CA6SNT studio in a project.
SkillCFreshness: CClaude Code +9 - 0.474score
qa-visual-criteria
6SNT-RADIO
For QA (08).
SkillCFreshness: CClaude Code +9 - 0.474score
data-integrity
6SNT-RADIO
For the Data Modeler (05).
SkillCFreshness: CClaude Code +9 - 0.471score
brand-evaluation-rubric
6SNT-RADIO
Grade visual identity with two A-F scores (Design Score / AI-Slop) and a 10 anti-pattern detector — makes principle P-03 measurable.
SkillCFreshness: CClaude Code +9 - 0.471score
security-audit
6SNT-RADIO
For Security (09).
SkillCFreshness: CClaude Code +9 - 0.471score
critic
6SNT-RADIO
Adversarial pre-gate review.
SkillCFreshness: CClaude Code +9 - 0.471score
architecture-decision
6SNT-RADIO
For the Architect (04).
SkillCFreshness: CClaude Code +9 - 0.467score
env-reproducible
6SNT-RADIO
For the Architect (04).
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 7, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/6SNT-RADIO/6SNT-Studio
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 6SNT-RADIO
- 0.474score
project-cleanup
6SNT-RADIO
For the Technical Writer (10).
SkillCFreshness: CClaude Code +9 - 0.474score
research-methodology
6SNT-RADIO
For the Researcher (02).
SkillCFreshness: CClaude Code +9 - 0.474score
smoke-test
6SNT-RADIO
'Done' includes an artifact that STARTS: an automated headless smoke with ONE command, pass/fail by exit code, and tests/smoke-result.json for the…
SkillCFreshness: CClaude Code +9 - 0.474score
data-integrity
6SNT-RADIO
For the Data Modeler (05).
SkillCFreshness: CClaude Code +9 - 0.474score
qa-visual-criteria
6SNT-RADIO
For QA (08).
SkillCFreshness: CClaude Code +9 - 0.474score
setup
6SNT-RADIO
Activates the CA6SNT studio in a project.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get adopt-ground running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
adopt-ground skill. Agent Mart. https://agentmart.dev/skills/6snt-radio-adopt-ground (last updated 2026-10-24)