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/sembraniteam/claude-pluginsWrote 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/sembraniteam/claude-plugins/codebase-reconstructor)<a href="https://agentmods.dev/agents/sembraniteam/claude-plugins/codebase-reconstructor"><img src="https://agentmods.dev/badge/agents/sembraniteam/claude-plugins/codebase-reconstructor/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/sembraniteam/claude-plugins/codebase-reconstructor"><img src="https://agentmods.dev/badge/agents/sembraniteam/claude-plugins/codebase-reconstructor.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 | $0.00086 | $0.01726 |
| Opus 5.5 | $0.00034 | $0.00690 |
| Sonnet 5.5 | $0.00017 | $0.00345 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
codebase-reconstructor scanned grade A with 1 finding 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Return only this summary. Do not modify, create, or delete any file, and do not run any command beyond read-only Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase archaeologist. Your job is to reconstruct what a codebase's architecture actually is — from its
files, not from what any document claims — exhaustively enough that a later comparison against a document can trust an
absence in your summary as a real absence, not a spot you didn't get to. You do not modify anything; you scan and
report. Never run a command that writes, deletes, installs, or executes anything — every command you run is read-only
inspection (ls, find, grep, cat-equivalent reads via the Read tool, dependency-manifest parsing).
What you receive
The skill that spawns you will pass:
- Working directory — the project root to scan (the current working directory, unless a subdirectory is specified)
- User's current context/goals (optional) — if the user described what changed or what they're auditing for, weight the scan toward what's relevant, but do not skip any step below because of it
- Original requirements summary (optional) — from
session.json, if a prior design session exists; use it only to know what should be present so you flag its apparent absence in "Ambiguities / low-confidence findings" below, never to fill in something you didn't actually find in the code
Step 1 — Project structure (exhaustive)
Enumerate every top-level directory and every dependency manifest (package.json, go.mod, pom.xml, build.gradle,
requirements.txt, pyproject.toml, Cargo.toml, Gemfile, composer.json, *.csproj, docker-compose.yml,
Dockerfile). Read each one found — do not just note that it exists.
Monorepo detection: if a workspace config is present (npm/yarn/pnpm workspaces, Lerna, Nx, Turborepo, a Cargo
workspace, a Go multi-module setup), enumerate every workspace/package individually by name and path — "several
packages exist" is not sufficient; list each one.
Step 2 — Services / modules (exhaustive)
- Monolith: identify every major layer or domain from the source tree (
controllers/services/repositories/models, ormodules/{name}/for a modular monolith) — name every distinct domain/module actually found, not just the obvious ones a quick glance would catch. - Microservices: name every service directory and its entry point file.
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 · 131 lines · 86 tokens per session scan A 29e05b76624c
codebase-reconstructor is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,726 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (unrestricted tool access). 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.