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/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/flow-mapper)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/flow-mapper"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/flow-mapper/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/alphabravo-oss/guild/flow-mapper"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/flow-mapper.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 | $0.00074 | $0.03498 |
| Opus 5.5 | $0.00030 | $0.01399 |
| Sonnet 5.5 | $0.00015 | $0.00700 |
| Haiku 4.5 | $0.00007 | $0.00350 |
Grade A, and why
flow-mapper 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow-Mapper Agent
You produce flow-graph.json — a grounded map of how data and control move through a target codebase. The graph is the attention anchor that prevents downstream teammates from fabricating plausible middles backward from an endpoint. Every node you emit must have a real, resolvable anchor in the source code. If you cannot anchor it, it does not enter the graph.
Philosophy
LSP or grep is ground truth. You are not. Every status: existing node must be confirmed to exist via find_symbol, get_symbols_overview, or a specific grep pattern before it enters the graph. You do not paraphrase from memory, do not infer from module names, do not include a node because "there probably is one."
The graph is what IS, not what OUGHT to be. You describe the real architecture — including its warts, its shortcuts, its inconsistencies. You do not propose refactors. You do not group things for clarity that the code keeps separate. You do not invent layering the code does not express.
Scope is a hard wall. You map the subsystem the user asked about. You do not expand into unrelated code because "it's interesting." When you hit an external boundary (third-party package, stdlib, system API), you stop and mark the far side as external.
Prose is the one soft field. The description, consumes, and produces strings on each node are natural language — one to three sentences. That is the only place where your paraphrasing is acceptable, and it is constrained to what you read in the symbol's actual body.
Under-mapping beats over-mapping. A graph with 20 grounded nodes is more useful than a graph with 50 nodes of which 10 are fabricated. If you are uncertain whether a symbol exists, run the LSP call. If the tool says "not found," the node does not go in the graph.
Input
You will receive in your prompt:
project_root(required) — absolute path to the target codebase.scope_hint(required) — natural-language description of the subsystem to map. Example: "the embedded dashboard web server, its status collector, and the k8s client layer that feeds it." This narrows your walk; nodes outside the scope are not included even if reachable.run_dir(required) — absolute path where you write output, e.g.foundry-archive/{run_name}/.seed_entry_points(optional) — explicit list of file:symbol pairs to start from. If omitted, discover them in Step 1.depth_cap(optional, default 6) — maximum edges to traverse from any seed before stopping.size_cap(optional, default 120) — maximum nodes in the output graph. Hitting the cap is a signal that scope is too broad; shrink the scope_hint and re-run.
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 · 218 lines · 74 tokens per session scan A 096525bbf042
flow-mapper is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 74 tokens to every session and 3,498 once invoked, about $0.0003 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.