Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Threat-Vector-Security/guardian-agent --skill coding-backend-orchestrationgit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/threat-vector-security/guardian-agent/coding-backend-orchestration)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/coding-backend-orchestration"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/coding-backend-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/coding-backend-orchestration"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/coding-backend-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00450 |
| Opus 5.5 | $0.00015 | $0.00180 |
| Sonnet 5.5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
coding-backend-orchestration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Coding Backend Orchestration
Overview / When to Use
Use this workflow only when the user explicitly wants Guardian to launch or inspect an external coding assistant.
This is distinct from normal repo-grounded coding work:
- if the user asks Guardian to inspect, edit, patch, search, or test code directly, stay on the built-in coding tools
- if the user explicitly says to use Codex, Claude Code, Gemini CLI, or Aider, launch that backend with
coding_backend_run - mentioning a backend as the subject of a question is not enough to relaunch it
Process
- Confirm the active coding session or list available sessions with
code_session_currentorcode_session_listif the target workspace is unclear. - If needed, inspect available backends with
coding_backend_list. - Launch the requested backend with
coding_backend_runfrom the active coding session workspace. - If the user is asking whether a delegated run finished or what happened, use
coding_backend_status. - After a backend run completes, verify the result with
code_git_diffand the strongest relevant checks such ascode_test,code_build, orcode_lint. - Report backend output as delegated work, not as if Guardian performed the edits directly.
Red Flags
- Treating "Why did Codex do that?" as permission to start a new Codex run.
- Launching an external backend when the user only asked for direct repo inspection.
- Reporting delegated backend work as successful without verification.
- Running a backend outside the active coding session workspace.
Verification
- The user explicitly requested an external coding backend.
- The delegated run stayed anchored to the active coding session workspace.
- You checked completion or recent runs with
coding_backend_statuswhen needed. - You verified the delegated result with
code_git_diff,code_test,code_build, orcode_lintbefore reporting success.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 39 lines · 37 tokens per session scan A abf686ce8ce2
coding-backend-orchestration is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 450 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…
analyzing-powershell-script-block-logging
Parse Windows PowerShell Script Block Logs (Event ID 4104) from EVTX files to detect obfuscated commands, encoded payloads, and living-off-the-land techniques. Uses python-evtx to extract and reconstruct multi-block scripts, applies entropy analysis and pattern matching for Base64-encoded commands, Invoke-Expression…
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
n8n-cli
Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance. Use when the user asks to interact with n8n, automate workflows, manage credentials, or operate their instance from the command line.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and workflowbuildercreatetasks silence rules. Load whenever any of these tags appear or after calling workflowbuildercreatetasks.