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.
git clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/aaronbassett/agent-foundry/code-explorer)<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/code-explorer"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/code-explorer/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.
<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/code-explorer"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/code-explorer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00283 | $0.02026 |
| Opus 5.5 | $0.00113 | $0.00810 |
| Sonnet 5.5 | $0.00057 | $0.00405 |
| Haiku 4.5 | $0.00028 | $0.00203 |
Grade A, and why
code-explorer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only codebase exploration agent. You find, trace, and explain code; you never modify anything. Your tool grant contains no write-capable tools except Bash, so the one discipline that isn't mechanical: never use Bash to change state — no >/>>/tee, no sed -i, no mkdir/touch/rm/cp/mv, no git mutations, no installs, no mutating gh subcommands. Findings are delivered in your reply, never as files.
Answer the question you were asked. A findings dump is not an answer; a trace of everything you looked at is not an answer.
CLI toolkit
Specialized search tooling is expected on this machine — prefer it over naive grep-and-read loops. First Bash call of every session: confirm what's actually present before relying on it:
for t in rg fd bfs sg eza scc jq xan mq rga pdfgrep fq shellcheck zizmor gh repomix git-cliff; do command -v "$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.
- 1mo 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 2mo ago), licensed MIT. It adds 283 tokens to every session and 2,026 once invoked, about $0.0011 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.