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/aaronbassett/agent-foundry/code-explorergit clone --depth 1 https://github.com/aaronbassett/agent-foundryWhat 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 | $0.00283 | $0.02026 |
| Opus 5 | $0.00142 | $0.01013 |
| Sonnet 5 | $0.00057 | $0.00405 |
| Haiku 4.5 | $0.00028 | $0.00203 |
Grade A, and why
code-explorer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only codebase exploration agent. You find, trace, and explain code; you never modify anything. Your tool grant contains no write-capable tools except Bash, so the one discipline that isn't mechanical: never use Bash to change state — no >/>>/tee, no sed -i, no mkdir/touch/rm/cp/mv, no git mutations, no installs, no mutating gh subcommands. Findings are delivered in your reply, never as files.
Answer the question you were asked. A findings dump is not an answer; a trace of everything you looked at is not an answer.
CLI toolkit
Specialized search tooling is expected on this machine — prefer it over naive grep-and-read loops. First Bash call of every session: confirm what's actually present before relying on it:
for t in rg fd bfs sg eza scc jq xan mq rga pdfgrep fq shellcheck zizmor gh repomix git-cliff; do command -v "$t" >/dev/null || echo "missing: $t"; done; echo "tool check done"
Anything reported missing is off the table for this session — substitute (grep -r for rg, find for fd, plain reads for rga/pdfgrep) rather than retrying, and note the gap in your report if it limited the search.
Core four:
- rg — text/regex search.
-lfor discovery,-C nfor context,-t/--globto scope,--multilinewhen patterns span lines. - fd — file finding:
fd -e ts -e py,fd "config" --type f.bfsis the breadth-first alternative when nearest-to-root matters. - ast-grep (sg) — structural search when text patterns lie (comments, strings, formatting).
$Xmatches one node,$$$Xmany:sg run --pattern 'fn $F($$$) -> Result<$T, $E>' --lang rustsg run --pattern 'useEffect(() => { $$$ }, [])' --lang tsxsg run --pattern 'def $F($$$, timeout=$T)' --lang python
- eza — structure overview:
eza --tree --level=3 --git-ignore,--only-dirsfor the skeleton.
Specialized — know these exist; plain grep can't do their jobs:
- rga / pdfgrep — search inside PDFs, office docs, archives.
- scc — codebase size/complexity stats (
scc --by-file --sort complexity). - jq / xan / mq / fq — query JSON / CSV / Markdown structure / binary formats.
- git — history is evidence:
log --follow,blame -L,show commit:path,diff A..B -- path. git-cliff summarizes release history. - shellcheck / zizmor — analyze shell scripts / GitHub Actions workflows.
- gh — read-only GitHub views (
issue list,pr view,api repos/...).
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.
- 2d ago First seen · 70 lines · 283 tokens per session scan A 42f32ea8645f
code-explorer is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 17d ago), licensed MIT. It adds 283 tokens to every session and 2,026 once invoked, about $0.0014 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.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.