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 skills add atretyak1985/swarmery --skill graftgit 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/skills/atretyak1985/swarmery/graft)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/graft"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/graft/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/skills/atretyak1985/swarmery/graft"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/graft.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 | $0.00102 | $0.01447 |
| Opus 5 | $0.00051 | $0.00724 |
| Sonnet 5 | $0.00020 | $0.00289 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
graft 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graft
graft is a context graph over the repo: every file and symbol as a node, calls/imports/contains as edges, kept next to the code in graft/. Its whole point is that finding code should cost one ranked answer, not a widening sequence of greps.
Requires the graft CLI on the machine (npm i -g @nanonets/graft). No API key and no model call for anything below — every command here is a local graph read.
Pick the command from the question
| The question you actually have | Command |
|---|---|
| "How does X work?" / "Where is X handled?" | graft ask "<question>" --source -n 5 |
| "Every place this string/pattern appears" | graft grep "<pattern>" |
| "What does this file expose?" | graft skeleton <path> |
| "Who calls this?" — before a rename or delete | graft callers <symbol> --depth 2 |
| "What does this call?" | graft callers <symbol> --direction out |
| "I have never seen this repo" | graft map |
--source is the flag that matters on ask: it inlines the code at each hit, so the
answer replaces opening the files rather than pointing at them. Reach for --full
only when a crux excerpt genuinely cut something you need.
Rules
- No index, no graft. If
graft/is absent, say so and use/search; do not build one mid-task without asking. askbeforegrep.askis ranked and graph-aware;grepis exhaustive and unranked. Usegrepwhen you need every occurrence, not to start a hunt.- Depth is a claim about risk. On
callers,d=1breaks,d=2probably breaks, deeper is a maybe.--depth allgives the full closure for a delete. - Confidence is not decoration.
extractededges come from the syntax tree;inferrededges were resolved heuristically — verify one before calling it a break. - A stale graph lies by omission. New callers it never saw read as "safe to change".
graft checkfails on staleness; a plaingraft buildis incremental. - Never report tokens saved. The graph is how you work, not a result to announce.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 101 lines · 102 tokens per session scan A 63b0a6b5cc3f
graft is a skill published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,447 once invoked, about $0.0005 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 2026-09-10.
Other skills, from other repositories
debugging
This skill should be used when a test is failing inexplicably, when a runtime error appears in production, when a bug reproduces unpredictably, or when two or more prior fix attempts have failed. Provides a 4-phase systematic debugging workflow — investigate, analyze patterns, form hypothesis, fix with test — to…
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
stall-reset
Reset CocoStall counters after an operator-approved recovery.
stall-thresholds
Show or update CocoStall thresholds.