Chalk Labs
Need help deploying posture?
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/prajapatimehul-posture
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/posture
What's inside
- Skill name
posture- Description
- Show current compliance posture across all findings
- License
- MIT
- Instructions
- 79 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /posture
Show a quick compliance posture summary. Read-only — does not spawn subagents.
## Instructions
Do NOT use the Agent tool. Handle this directly.
### 1. Read All Findings
Use Glob to find all `.compliance/findings/FINDING-*.json` files, then Read each one.
If no findings exist, report:
```
No findings found. Run /scan first to assess your AWS account.
```
### 2. Compute Statistics
Count findings by:
- **Status**: open, in_progress, remediated, verified, skipped
- **Severity**: critical, high, medium, low
- **Service**: group by `source.service`
- **Framework**: group by `compliance[].framework`
Calculate compliance percentage:
```
compliance% = (verified + skipped) / total * 100
```
### 3. Display Summary
```
# Compliance Posture
Last scan: {most recent scanId from findings}
Total findings: {n}
## By Status
| Status | Count |
|--------|-------|
| Open | {n} |
| In Progress | {n} |
| Remediated | {n} |
| Verified | {n} |
| Skipped | {n} |
## By Severity
| Severity | Open | Fixed | Total |
|----------|------|-------|-------|
| Critical | {n} | {n} | {n} |
| High | {n} | {n} | {n} |
| Medium | {n} | {n} | {n} |
| Low | {n} | {n} | {n} |
## By Framework
| Framework | Controls Hit | Findings | Verified | Score |
|-----------|-------------|----------|----------|-------|
| SOC 2 | {n unique controls} | {n} | {n} | {%} |
| HIPAA | {n unique controls} | {n} | {n} | {%} |
## By Service
| Service | Open | Fixed | Total |
|---------|------|-------|-------|
| s3 | {n} | {n} | {n} |
| iam | {n} | {n} | {n} |
| ... | ... | ... | ... |
## Top Open Issues
{List top 5 open findings by severity, with finding ID, check title, and resource}
```
### 4. Framework Filter
If `$ARGUMENTS` contains `--framework soc2` or `--framework hipaa`:
- Only show findings mapped to that framework
- Adjust all counts accordinglyFrom prajapatimehul/comp-agent, MIT.
More from prajapatimehul/comp-agent
- 0.458score
remediate
prajapatimehul
Fix open compliance findings with evidence capture and human approval
SkillDFreshness: D★ 5Claude Code +9 - 0.458score
scan
prajapatimehul
Run a Prowler compliance scan against your AWS account (SOC2 + HIPAA)
SkillDFreshness: D★ 5Claude Code +9 - 0.458score
audit-report
prajapatimehul
Generate an audit-ready compliance report grouped by SOC2 and HIPAA controls
SkillDFreshness: D★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 2, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/prajapatimehul/comp-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from prajapatimehul
- 0.458score
remediate
prajapatimehul
Fix open compliance findings with evidence capture and human approval
SkillDFreshness: D★ 5Claude Code +9 - 0.458score
scan
prajapatimehul
Run a Prowler compliance scan against your AWS account (SOC2 + HIPAA)
SkillDFreshness: D★ 5Claude Code +9 - 0.458score
audit-report
prajapatimehul
Generate an audit-ready compliance report grouped by SOC2 and HIPAA controls
SkillDFreshness: D★ 5Claude 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 posture 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
posture skill. Agent Mart. https://agentmart.dev/skills/prajapatimehul-posture (last updated 2026-10-24)