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/systematic-debuggingnpx skills add Threat-Vector-Security/guardian-agent --skill systematic-debugginggit 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 | $0.00025 | $0.00711 |
| Opus 5 | $0.00013 | $0.00356 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
systematic-debugging 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Overview / When to Use
Do not guess. Find the root cause before changing code, config, or prompts. No fixes without investigation first. If you have not reproduced the issue, read the errors, and traced where the bad state comes from, you are not ready to fix it.
Process
- Capture the exact failure.
- Record the command, request, or user action that fails.
- Read the full error output, stack trace, and relevant logs.
- If the issue is intermittent, collect enough evidence to describe the pattern.
- Reproduce the issue consistently.
- Prefer the narrowest reliable reproduction.
- If you cannot reproduce it, gather more evidence instead of guessing.
- Check recent changes and working examples.
- Look at the diff, config changes, dependency changes, and comparable working code paths.
- Trace backward to the source of the bad value or state.
- Start where the failure appears.
- Keep moving backward until you find where the wrong input, assumption, or transition originated.
- Form one hypothesis and test it with the smallest useful change.
- Change one thing at a time.
- If the hypothesis fails, return to investigation with the new evidence.
- Add a regression test or equivalent reproducible check before the permanent fix.
- Verify the fix with the original reproduction and the regression test.
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "I know what this is, I'll just fix it." | Guessing leads to incomplete fixes or new bugs. Reproduce and trace it first. |
| "I'll try fixing three things at once to save time." | Multiple changes obscure which one actually fixed the issue or introduced regressions. Change one thing at a time. |
| "I'll skip the regression test since I manually verified it." | If it broke once, it will break again. Add a reproducible check before calling it done. |
Red Flags
Stop and return to investigation if you catch yourself:
- proposing multiple fixes at once
- saying "it is probably X"
- patching symptoms without tracing source state
- skipping a failing test because manual verification seems faster
- trying a fourth fix after three failed attempts (this means the architecture or assumption is wrong)
What ships with it
4 files 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.
- 2d ago First seen · 67 lines · 25 tokens per session scan A 491cf0a4b16d
systematic-debugging 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 25 tokens to every session and 711 once invoked, about $0.0001 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…