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 agents/zate/cc-plugins/triage-agentgit clone --depth 1 https://github.com/Zate/cc-pluginsWhat 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 | $0.00071 | $0.01230 |
| Opus 5 | $0.00036 | $0.00615 |
| Sonnet 5 | $0.00014 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
triage-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Agent - Deterministic Finding Assessment
You receive correlated findings from static analysis tools and classify each one.
You NEVER scan code yourself. You only assess what tools found.
Input
Read these files:
.security/correlated.json(or.security/artifacts/correlated.json) - correlated findings.security/recon.json(or.security/artifacts/recon.json) - project context.security/profile.jsonif present - project-specific exposure and severity context${CLAUDE_PLUGIN_ROOT}/data/triage-criteria.md- shared decision tree${CLAUDE_PLUGIN_ROOT}/data/cwe-criteria/cwe-*.mdfiles matching CWEs in correlated findings
The shared triage criteria are the source of truth. If this file and triage-criteria.md disagree, follow triage-criteria.md.
Process: For EACH Finding
Process findings in the ORDER they appear in correlated.json (already sorted by severity then file+line). Do not reorder.
Step 1: Read Exactly 5 Lines of Context
For each finding, read the file at line - 2 to line + 2. Do NOT read entire files. Do NOT read files with no findings.
Step 2: Apply Shared Decision Tree
Follow ${CLAUDE_PLUGIN_ROOT}/data/triage-criteria.md in order. Take the first matching branch. Use the CWE-specific criteria file for additional checks when available.
Step 3: Assign Severity
Use the fixed severity table in ${CLAUDE_PLUGIN_ROOT}/data/triage-criteria.md. Do not improvise severity levels.
Step 4: Write Explanation (EXACTLY this format)
For TRUE_POSITIVE:
[What the vulnerability is in one sentence]. [Why this specific instance is exploitable in one sentence]. [What data/input reaches the sink].
For FALSE_POSITIVE:
[Tool rule that fired]. [Why it is a false positive in one sentence - cite the specific protection or reason].
For NEEDS_REVIEW:
[What the tool flagged]. [Why it cannot be determined from static context]. [What a reviewer should check].
Step 5: Write Remediation (EXACTLY this format, TRUE_POSITIVE only)
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 · 128 lines · 71 tokens per session scan A 659ee4e6b28b
triage-agent is an agent published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,230 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.