agentsec-report

agentsec-report is a command for coding agents from kernora-ai/agent-sec. It costs 31 tokens per session (365 once invoked), scanned A, original, Apache-2.0.

A local report command for reviewing security warnings recorded during your own agent sessions.

In plain words
What is it for?
Use it to count flagged actions, see when they started, count rule references, and identify commonly flagged command types.
Why use it?
It shows how often the local security check flagged risky actions without sending the log elsewhere.

Command

Part of the kernora-agent-security plugin — 1 skill, 3 commands, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/kernora-ai/agent-sec/agentsec-report
Clone the repo
git clone --depth 1 https://github.com/kernora-ai/agent-sec

Or install kernora-agent-security, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 hook.

Wrote 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.

agentmods badge for agentsec-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/kernora-ai/agent-sec/agentsec-report.svg)](https://agentmods.dev/commands/kernora-ai/agent-sec/agentsec-report)
Your own site
<a href="https://agentmods.dev/commands/kernora-ai/agent-sec/agentsec-report"><img src="https://agentmods.dev/badge/commands/kernora-ai/agent-sec/agentsec-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00365
Opus 5 $0.00015 $0.00182
Sonnet 5 $0.00006 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 4d ago against content hash 2f46333e4f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentsec-report 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.

plugins/kernora-agent-security/commands/agentsec-report.md · 24 lines

What it actually says

Read the LOCAL advisory log and summarize it for the user. Run:

!python3 - <<'PY' import json,os,collections,time p=os.path.expanduser("~/.agentsec/flags.log") if not os.path.exists(p): print("No flags yet — the advisory hook hasn't caught anything in your sessions (or isn't enabled)."); raise SystemExit rows=[json.loads(l) for l in open(p) if l.strip()] if not rows: print("No flags recorded yet."); raise SystemExit total=len(rows); rules=sum(r.get("rules",0) for r in rows) first=time.strftime("%Y-%m-%d",time.localtime(min(r["t"] for r in rows))) print(f"Kernora Agent Security — your local effectiveness view (nothing left your machine):") print(f" {total} risky action(s) flagged since {first}; {rules} rule-citation(s) surfaced.") c=collections.Counter(r["cmd"].split()[0] if r.get("cmd") else "?" for r in rows) print(" most-flagged command starts: " + ", ".join(f"{k}×{v}" for k,v in c.most_common(5))) PY

Then explain: this is a LOCAL view only (we store nothing server-side — the free tier is stateless and private). Full per-action reporting with a tamper-evident, cited audit ledger is the paid Kernora Axiora Integrity Plane.

Changes

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.

  1. 4d ago First seen · 24 lines · 31 tokens per session scan A 2f46333e4f02

Subscribe to this mod's changes

agentsec-report is a command published in the GitHub repository kernora-ai/agent-sec (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 365 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 2026-08-31.