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 amitvijapur/cortex --skill cortex-loggit clone --depth 1 https://github.com/amitvijapur/cortexWrote 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/amitvijapur/cortex/cortex-log)<a href="https://agentmods.dev/skills/amitvijapur/cortex/cortex-log"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-log/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/amitvijapur/cortex/cortex-log"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-log.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 | $0.00051 | $0.00427 |
| Opus 5.5 | $0.00020 | $0.00171 |
| Sonnet 5.5 | $0.00010 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
cortex-log 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 6d 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
/cortex-log
Show the last N Cortex routing decisions from the active state's cortex-log.jsonl with full reasoning.
When to invoke
- User types
/cortex-logexplicitly - User asks "what routes have I been using"
- User asks "what did cortex pick for X"
- User says "show me recent routing decisions"
- User says "audit my recent routes"
What to do
Run the cortex show command and print its output verbatim. Nothing else.
Resolve the state directory from CORTEX_HOME, then CLAUDE_DIR, then
$HOME/.claude, matching the CLI and installer. Keep a custom override exported
in the agent's environment.
cortex_state_dir="${CORTEX_HOME:-${CLAUDE_DIR:-$HOME/.claude}}"
python3 "$cortex_state_dir/bin/cortex" show --last 20
Optional args:
--last N— show last N routes instead of 20--project <name>— filter to a specific project
What the user sees
Each entry shows:
- Timestamp, project, task classification
- The original task description
- The chosen route (
System > Pattern > Agent @ Tier) - The reasoning tags (why this tier, why this system) — or
(obvious route)when no tags were recorded
If the log is empty, the command prints cortex log is empty — no routes logged yet.
Do NOT
- Do not aggregate or summarize the output — the user wants per-decision visibility, not stats
- Do not filter out routes unless the user explicitly asks
- Do not add commentary unless the user asks a follow-up question
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.
- 6d ago Changed · +5 lines 5804dfb4e665
- 1mo ago First seen · 46 lines · 51 tokens per session scan A 9104cb84e5da
cortex-log is a skill published in the GitHub repository amitvijapur/cortex (5 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 427 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
py-debug
Python debugging expert. Use when the user needs to debug, profile, or trace Python code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function".
bug-report-reproduce
Reproduce a user, customer, or support-reported problem with synthetic data, prove the cause with a temporary test, record a narrated click-through walkthrough of the symptom, and report what was and was not proven. Use when the user links a bug report, support thread, or ticket and asks to reproduce it, find the…
changes-explain
Explain a pull request, commit range, branch, or local diff from a system-design perspective. Use for practical understanding of changed behavior, boundaries, flow, ownership, operations, risks, and verification rather than defect review.
work-audit
Evidence-first, read-only audits that always use one gpt-5.6-sol xhigh analyst and return a self-contained fix plan suitable for a lower-capability execution model. Use when the user asks to audit code, a diff, a branch, an artifact, or a runtime flow.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.