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/atretyak1985/swarmeryWrote 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/commands/atretyak1985/swarmery/impact)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/impact"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/impact.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 | $0.00018 | $0.01533 |
| Opus 5 | $0.00009 | $0.00766 |
| Sonnet 5 | $0.00004 | $0.00307 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
impact 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact Analysis Command
Find everything affected by a change to: $ARGUMENTS
Primary path — Graphify (graph-aware, most accurate)
Graphify builds a per-repo knowledge graph at <repo>/graphify-out/graph.json. Each repo from
project.json → repos has its own graph — run the commands from inside the repo you are
analyzing (or pass --graph <repo>/graphify-out/graph.json explicitly).
- Blast radius —
graphify affected "$ARGUMENTS" --depth 3— reverse traversal listing everything that depends on the symbol (run per repo: the main app fromproject.json → mainApp, then the device/edge repo fromproject.json → deviceif the project has one). - Connection trace —
graphify query "what depends on $ARGUMENTS?"for a BFS answer, orgraphify path "$ARGUMENTS" "<other symbol>"to prove/disprove a specific dependency. - Symbol context —
graphify explain "$ARGUMENTS"— the node, its neighbors, and its community, with file:line citations. - Weigh edge confidence:
EXTRACTEDedges come straight from the AST (trust them);INFERREDedges were model-resolved (verify before calling them WILL BREAK).
If the staleness hook warns the graph is behind HEAD, run
graphify update .first (add--forceafter refactors that deleted files) — otherwise the blast radius may omit new callers (a false "safe to change").
Fallback path — ripgrep (always live; covers anything the graph misses)
Use ripgrep whenever the graph is stale or absent, and to double-check infra config
(deploy manifests/YAML) if it is not in the graph. Run from the workspace root, listing
the repos from project.json → repos:
rg -n --no-heading "$ARGUMENTS" \
apps/<mainApp> <device-repo> \
<infrastructure-repo>
What to report
- Total occurrences + per-repo breakdown.
- File paths with line numbers and surrounding context.
- For graph results: depth (
d=1WILL BREAK /d=2LIKELY /d=3MAYBE) and the edge confidence tag (EXTRACTEDvsINFERRED). - Recommended update order if the symbol changes (interfaces → impls → callers → tests).
- Cross-tier flag: if the symbol crosses the main app ↔ the device/edge repo, call out the manual contract (no shared schema) and the coordinated-merge requirement.
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 · 135 lines · 18 tokens per session scan A e7d5e119451c
impact is a command published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 1,533 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
gws-keep
List and read Google Keep notes.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
excalidraw
Create or modify an editable Excalidraw diagram.
debugger
Systematic debugging with TodoWrite and Memory integration.
fix-renovate-mr
Fix renovate issues.