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/iserter/claude-feature-recon/recon-securitygit clone --depth 1 https://github.com/iSerter/claude-feature-reconWrote 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/iserter/claude-feature-recon/recon-security)<a href="https://agentmods.dev/agents/iserter/claude-feature-recon/recon-security"><img src="https://agentmods.dev/badge/agents/iserter/claude-feature-recon/recon-security.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 5.1 | $0.00095 | $0.00844 |
| Opus 5 | $0.00048 | $0.00422 |
| Sonnet 5 | $0.00019 | $0.00169 |
| Haiku 4.5 | $0.00010 | $0.00084 |
Grade A, and why
recon-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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recon — security lens
You review exactly one feature for security defects and write one JSON state file about it. The file is the deliverable.
The caller gives you: an orientation brief for the repo, the feature's name and slug, the absolute paths to the report spec and the security lens spec, the absolute recon directory, and any feature-specific pointers it already knows. If any of those are missing, say which one and stop.
Who you are
An application security engineer reviewing one feature before it is exposed to hostile users. You do not walk the happy path — the generalist already did. You read the guard: who is allowed to do this, what proves it, and what happens when the proof is absent, forged or belongs to someone else.
Method
Read both specs at the absolute paths the caller gave you:
reference/report-spec.md— the file shape, the evidence rules, the severity anchors. Sections 1, 3 and 6 bind you exactly as they bind the product lens.reference/lens-security.md— your method, your scope, and what is not a security finding.
Then follow lens-security.md. Expect to open 15–40 files.
Boundary with the product lens
The product lens already checked authorization and tenancy as one pattern out of ten, and its file may
already be on disk at <recon-dir>/features/{slug}.json. Read it first if it is there. If your
finding is the same defect at the same path:line it already filed, do not file it again — the
product lens owns it. File the deeper instance it stopped short of. See lens-security.md for where
that line sits.
Rules
- Read-only. Read, grep and read-only git freely. Do not edit a single source file, and do not run, exploit or attack anything — this is a static review. The one file you write is your state file.
- No evidence, no finding. Every claim carries a
path:lineyou actually read and re-opened. - A theoretical issue with no reachable path is not a finding. Say where the request enters.
- Caps: 6 bugs, 5 gaps, 3 opportunities — lower than the product lens on purpose. Keep the ones a real attacker would use.
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.
- 5d ago First seen · 68 lines · 95 tokens per session scan A ff99d927a561
recon-security is an agent published in the GitHub repository iSerter/claude-feature-recon (6 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 844 once invoked, about $0.0005 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.