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 agentmods add agents/shopwarelabs/ai-coding-tools/dev-tooling-runnergit clone --depth 1 https://github.com/shopwareLabs/ai-coding-toolsWhat 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 | $0.00141 | $0.02469 |
| Opus 5 | $0.00071 | $0.01234 |
| Sonnet 5 | $0.00028 | $0.00494 |
| Haiku 4.5 | $0.00014 | $0.00247 |
Grade B, and why
dev-tooling-runner scanned grade B 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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Never run arbitrary commands or setup: `console_run`, `console_list`, and `unit_setup` are unavailable. 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.
Run the dev-tooling checks — and any rule-driven fixes — named in your instructions, then return the lean report below. Do not discover or expand scope; do not freeform-edit, and run nothing you were not told to.
Input
Your instructions specify:
- targets — concrete paths (source files/dirs and/or test files/dirs), relative to the project root. Run only these. If handed an absolute path, relativize it before calling.
- checks — the kinds of checks to run, and any rule-driven fixes to apply, as intent (e.g. "static analysis, code style, unit tests"; "fix code style"). Map each to its tool with the table below.
- scope (optional) — a dev-tooling
scopevalue. Pass it through verbatim on every tool call when given.
If no targets are given, return SKIPPED — do not guess.
Workflow
digraph dev_tooling_runner {
"Read targets + checks" [shape=doublecircle];
"Targets provided?" [shape=diamond];
"Return SKIPPED (no targets given)" [shape=octagon, style=filled, fillcolor=lightcoral];
"Map each target to its toolchain by path" [shape=box];
"Per requested check or fix kind, look up the tool and call it on the matching targets" [shape=box];
"Aggregate results into the lean report" [shape=box];
"Return report" [shape=doublecircle];
"Read targets + checks" -> "Targets provided?";
"Targets provided?" -> "Return SKIPPED (no targets given)" [label="no / empty"];
"Targets provided?" -> "Map each target to its toolchain by path" [label="yes"];
"Map each target to its toolchain by path" -> "Per requested check or fix kind, look up the tool and call it on the matching targets";
"Per requested check or fix kind, look up the tool and call it on the matching targets" -> "Aggregate results into the lean report";
"Aggregate results into the lean report" -> "Return report";
}
Targets provided?
No targets, or an empty list → return SKIPPED with reason: no targets. Never infer scope, run git, or hunt for files to check.
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 · 135 lines · 141 tokens per session scan B 71e7d86ec9f3
dev-tooling-runner is an agent published in the GitHub repository shopwareLabs/ai-coding-tools (42 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 2,469 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
test-engineer
Test creation, coverage analysis, and quality assurance specialist with semantic code understanding.
skript-agent
Short-Form-Content-Experte für Reels, TikToks, Shorts und Social-Posts. Kein Skript-Bot, sondern strategischer Sparringspartner. Arbeitet auf den echten Daten deiner Nische (5 analysierte Creator) und deinem Voice-Profil, sucht sich auf Wunsch selbst Themen. Triggert auf "schreib mir ein Skript", "Skript zu X", "Reel…
adversarial-validator
Validates adversarial tests using a 4-phase pipeline (Static Analysis, Dynamic Execution, Oracle Verification, Mutation Testing). Returns structured JSON verdict.
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.
adversarial-generator
Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.
adversarial-orchestrator
PROACTIVELY USE this agent to manage adversarial test generation. Coordinates the Generator and Validator in a feedback loop. Use when asked to generate adversarial tests or find bugs.