talocode-agent-control-plane
Gate agent tool calls, spend, policy, and verify output before merge using Talocode control-plane products.
Skill by talocode
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/talocode-talocode-agent-control-plane
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: agent-building
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/talocode-agent-control-plane
What's inside
- Skill name
talocode-agent-control-plane- Description
- Gate agent tool calls, spend, policy, and verify output before merge using Talocode control-plane products.
- License
- MIT
- Instructions
- 77 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# Talocode agent control plane
Use this skill whenever an agent is about to call tools, spend credits, or open a PR with generated code.
## Order of operations
1. **SpendCaps** — can we afford this action?
2. **GateLane** — is this tool allowed for this actor?
3. **PolicyLane** — role/tag policy + redact secrets from payloads
4. **Execute tool** (only if allowed)
5. **VerifyLane** — scan code/diff/agent output before merge
6. **Tera coding/review** (optional paid depth) for high-risk changes
7. **Skills** — package reusable agent instructions via Skills API
## Local (no key)
```bash
# GateLane open-source gateway
npx @talocode/gatelane demo
# VerifyLane
npx verifylane code --file ./src/app.ts
# Demo path
node demo/agent-control-plane/ship-demo-core.js
```
## Hosted (TALOCODE_API_KEY)
Base: `https://api.talocode.site`
```bash
# Guard tool call (denies dangerous tools by default)
curl -sS -X POST "$TALOCODE_BASE_URL/v1/gatelane/guard" \
-H "Authorization: Bearer $TALOCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"shell.exec","actor":"agent-1","policies":[]}'
# Policy check
curl -sS -X POST "$TALOCODE_BASE_URL/v1/policylane/check" \
-H "Authorization: Bearer $TALOCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"action":"tool.shell","policy":{"defaultEffect":"deny","rules":[{"action":"tool.shell","effect":"deny"}]}}'
# Verify code
curl -sS -X POST "$TALOCODE_BASE_URL/v1/verifylane/code" \
-H "Authorization: Bearer $TALOCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"eval(x)"}'
# Spend cap
curl -sS -X POST "$TALOCODE_BASE_URL/v1/spendcaps/check" \
-H "Authorization: Bearer $TALOCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"balanceCredits":100,"costCredits":5,"spentInWindow":10,"windowLimit":50}'
```
## Credits (approx)
| Action | Credits |
|--------|---------|
| gatelane.check | 2 |
| gatelane.guard | 3 |
| policylane.check | 2 |
| verifylane.code | 8 |
| spendcaps.check | 1 |
| skills generate repo | 100 |
| tera coding/review | 20 |
## Rules
- Default **deny** for write/shell/network-internal tools
- Never ship agent output with critical/high VerifyLane findings
- Prefer open-source CLIs for local; bill hosted power for team CI
- Do not name external competitor products in public Talocode copyFrom talocode/skills, MIT.
More from talocode/skills
- 0.524score
talocode-content-agent
talocode
Create original, evidence-led Talocode and TeraAI content through a repeatable brief-to-improvement loop.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-design-taste-router
talocode
Route design tasks to the right Talocode design skill — frontend UI polish, partnership graphics, video design, and release demos.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-agent-native-protocol
talocode
Design native agent capabilities for Talocode products — typed, permissioned, audited action registries and context providers for multi-surface use (UI…
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-agent-workflows
talocode
Define structured workflows for coding agents working on real software projects — TDD, code review, git, PRs, releases, and multi-step implementations.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-architecture-design
talocode
Design and review codebase and API architecture using deep modules — lots of behaviour behind a small interface placed at a clean, testable seam.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-bug-diagnosis
talocode
Repeatable, feedback-loop-first process for diagnosing bugs — build a tight, deterministic, red-capable signal before generating any hypotheses.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-code-review
talocode
Review changes along two independent axes (Standards and Spec) using parallel sub-agents so one axis doesn't mask the other.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-codebase-search
talocode
Search codebases before making changes — locate command handlers, API routes, config files, provider usage, and function implementations.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-context-engineering
talocode
Help agents maintain focus and accuracy during extended coding sessions by managing context effectively across large refactors and multi-file workflows.
SkillBFreshness: BClaude Code +9 - 0.521score
contextlane
talocode
ContextLane — open-source context ingestion pipeline for persistent AI agents.
SkillBFreshness: BClaude Code +9 - 0.521score
screen-recording-skill
talocode
Turn screen recordings into reusable agent skills by extracting steps, actions, and UI patterns from video frames into a structured SKILL.md.
SkillBFreshness: BClaude Code +9 - 0.515score
reliabilitylane
talocode
ReliabilityLane — Talocode agent skill
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Aug 10, 2026 (2 months ago)
- Last release
- Jul 22, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/talocode/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from talocode
- 0.587score
talocode-cloud
talocode
Use Talocode Cloud APIs and $TCODE hold-to-earn credits.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
cloudflare
talocode
Use Cloudflare for Talocode infrastructure.
SkillAFreshness: A★ 1Claude Code +9 - 0.524score
talocode-content-agent
talocode
Create original, evidence-led Talocode and TeraAI content through a repeatable brief-to-improvement loop.
SkillBFreshness: BClaude Code +9 - 0.521score
screen-recording-skill
talocode
Turn screen recordings into reusable agent skills by extracting steps, actions, and UI patterns from video frames into a structured SKILL.md.
SkillBFreshness: BClaude Code +9 - 0.521score
contextlane
talocode
ContextLane — open-source context ingestion pipeline for persistent AI agents.
SkillBFreshness: BClaude Code +9 - 0.521score
talocode-agent-workflows
talocode
Define structured workflows for coding agents working on real software projects — TDD, code review, git, PRs, releases, and multi-step implementations.
SkillBFreshness: BClaude Code +9
Cite this page
talocode-agent-control-plane skill. Agent Mart. https://agentmart.dev/skills/talocode-talocode-agent-control-plane (last updated 2026-10-24)