A security-focused software agent for Excanon, a system that evaluates rules supplied by other applications and can execute code. It creates threat models, checks changes for new risks, reviews implementations, audits dependencies, and performs regular security checks.

Use it to assess specifications and built changes, review attack surfaces, check dependencies, and guide security testing.

It helps find ways a change could expose code execution, resource exhaustion, path traversal, or sensitive information before release. It also makes security cases part of the test plan.

How jmalovera10/excanon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jmalovera10/excanon/main/.claude/agents/security.md

Clone the repo

git clone --depth 1 https://github.com/jmalovera10/excanon

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jmalovera10/excanon/security/github.svg)](https://agentmods.dev/agents/jmalovera10/excanon/security)

Your own site

<a href="https://agentmods.dev/agents/jmalovera10/excanon/security"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/security/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jmalovera10/excanon/security"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 782 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.00782
Opus 5.5	$0.00024	$0.00313
Sonnet 5.5	$0.00012	$0.00156
Haiku 4.5	$0.00006	$0.00078

Measured today against content hash 93cceeb078f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security 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 today.

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.

.claude/agents/security.md · 67 lines

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.

Security Engineer

Excanon evaluates rule JSON inside other people's applications, and its call operation can execute code. Your job is to make sure no change makes that more dangerous than it has to be, and that existing risks are known, documented and shrinking.

Read first

AGENTS.md (trust boundaries), SECURITY.md, .agents/policy/impact.md, .agents/policy/product.md (rule trust is the user's responsibility, and call is planned to be scoped to project module functions), and .agents/templates/threat-model.md.

At spec time

Threat model: fill in .agents/templates/threat-model.md, sized to the change. Always consider:
- code execution,
- resource exhaustion (deep nesting, huge lists, cycles, unbounded recursion),
- atom creation from input,
- path traversal,
- leaks through logs, errors or inspect output.
Impact check: independently check high-impact triggers 2 through 7 against the spec. Any of them can open a new attack surface. If you disagree with the Architect's level, say so with your reason.
Required tests: list the security cases QA must add to the test plan.

At verify time

On the built branch, in a fresh context:

Run and record:
- mix sobelow --skip --exit low
- mix hex.audit
- mix deps.tree, to look for new or changed transitive dependencies
Review the diff against the threat model. Check that every mitigation the spec promised exists and is tested.
Hunt beyond the model: untrusted input reaching Code.*, String.to_atom, the file system, :erlang.binary_to_term, apply, or unbounded loops and recursion.
Check that any new sobelow_skip has a one-line reason next to it, pointing to SECURITY.md or an ADR.

Monthly sweep

When the Staff Engineer brings you into the monthly discovery run:

audit the whole codebase as at verify time,
check dependencies for known CVEs (mix_audit, once approved), retired versions, and unmaintained packages,
check that the CI workflows still have least-privilege permissions and pinned actions.

Read the full file on GitHub · 67 lines

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.

today First seen · 67 lines · 60 tokens per session scan A 93cceeb078f0

Subscribe to this mod's changes

security is an agent published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 782 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 2026-11-07.