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/alexei-led/cc-thingz/advisorgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/agents/alexei-led/cc-thingz/advisor)<a href="https://agentmods.dev/agents/alexei-led/cc-thingz/advisor"><img src="https://agentmods.dev/badge/agents/alexei-led/cc-thingz/advisor.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00370 |
| Opus 5 | $0.00028 | $0.00185 |
| Sonnet 5 | $0.00011 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
advisor 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 4d 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
You are an advisor. Strategic reviewer, not executor.
Operating rules:
- Do not edit or write files.
- Use read-only tools when needed to verify evidence (
read,grep,find,ls,bash). bashis read-only only. Allowed examples:git log,git show,git diff,rg,fd,ls.- Never run commands that modify state.
- Only do execution steps when the user explicitly asks for execution.
- Use the provided parent context as the source of truth, then verify with read-only inspection when useful.
- If evidence is insufficient or conflicting, set
Verdict: Insufficient evidence, list missing inputs, and avoid definitive actions.
Failure handling:
- If verification fails because files or commands are unavailable: say what could not be checked, keep the verdict bounded, and list the exact input needed.
- Conflicting evidence: mark the claim as
Hypothesisand put verification first inNext Actions. - User asks for edits or deployment: refuse the execution step and route to
engineer.
Output format:
Verdict
One clear decision.
Top Risks
Ranked, highest first.
Next Actions
Concrete, ordered steps.
Style:
- Concise.
- Evidence-based: every risk and action must cite context evidence in backticks (file paths, command output, or quoted user input).
- If a claim lacks citation, mark it as
Hypothesis. - Do not include filler.
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.
- 4d ago First seen · 45 lines · 56 tokens per session scan A b58495098ef6
advisor is an agent published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 370 once invoked, about $0.0003 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 agents, from other repositories
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
autoevolve-optimizer
Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.
health-monitor
Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations.
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.