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 agentmods add skills/threat-vector-security/guardian-agent/coding-workspacenpx skills add Threat-Vector-Security/guardian-agent --skill coding-workspacegit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWhat 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 | $0.00035 | $0.00798 |
| Opus 5 | $0.00017 | $0.00399 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
coding-workspace 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Workspace
Overview / When to Use
Use this workflow for backend-owned coding sessions inside a project workspace when Guardian should do the coding work directly with built-in tools.
Explicit delegation to terminal-backed coding assistants such as Codex, Claude Code, Gemini CLI, or Aider belongs to the separate coding-backend-orchestration workflow.
The coding session is the authoritative project context:
- use the backend session’s workspace root, workspace profile, indexed repo map, working-set files, focus summary, selected file, and recent work as your default context
- keep repo-local actions inside that workspace
- do not preload host-application context when reasoning inside the coding session
- use the coding session’s own long-term memory as the default memory scope; do not assume global memory is available unless explicitly bridged
- you may still use broader tools and capabilities, including non-coding tasks, but do not let that replace the session’s repo anchor unless the user explicitly changes sessions or retargets the work
Process
- If the user wants to continue existing coding work, inspect the current attachment with
code_session_currentor list sessions withcode_session_list. - If no suitable session exists, create one with
code_session_create, then treat that backend session as the shared source of truth across web, CLI, and Telegram. Shared session state does not mean those surfaces have the same UI or transport. - Understand the request and inspect the relevant files or symbols first. Treat the workspace profile, indexed repo map, and current working set as the default project context, but re-read files before making concrete claims or edits.
- Create or update a concise plan with explicit acceptance gates before broad or multi-file edits.
- Make the smallest safe change with
code_edit,code_patch, orcode_create. Prefer patches for multi-hunk changes and targeted edits for isolated replacements. - Verify with
code_git_diffand the strongest existing relevant checks before falling back to narrower ad hoc tests. - If the session is getting noisy, summarize progress so it can be compacted without losing the plan.
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.
- 3d ago First seen · 54 lines · 35 tokens per session scan A 493cbacba36d
coding-workspace is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 798 once invoked, about $0.0002 per session on Opus 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
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
agentfootprint
Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.
billing
Use for refunds, disputed charges, invoices and any billing question.
shipping
Use for delivery estimates, lost parcels and address changes.
agentfootprint
Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.
titanclip
Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…