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 rjwalters/kicad-tools --skill loom-cargo-target-isolationgit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/rjwalters/kicad-tools/loom-cargo-target-isolation)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/loom-cargo-target-isolation"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-cargo-target-isolation/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/rjwalters/kicad-tools/loom-cargo-target-isolation"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-cargo-target-isolation.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 | $0.00070 | $0.01400 |
| Opus 5.5 | $0.00028 | $0.00560 |
| Sonnet 5.5 | $0.00014 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade C, and why
loom-cargo-target-isolation scanned grade C 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 27d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
printed path (`rm -rf /tmp/cargo-target-123`). The `rmScope` guard 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.
Shared Cargo Target Dir: Isolation Recipe (#8457)
Load when: you are about to run (or just ran) a local cargo build/cargo test/cargo run whose result will inform a verdict — a Judge approval or
rejection, a Doctor "the fix works", or a Builder "tests pass" before opening
a PR.
Why this exists
A fleet host with one shared cargo target directory uplifts every workspace
binary to a single un-hashed path (e.g. target/debug/loom-daemon). Cargo
overwrites that path whenever another worktree builds concurrently. An
integration test that executes it can therefore observe a different
worktree's binary, silently. On 2026-09-20 this produced three real
false-verdict incidents in one day: a Judge saw 12 false failures from a
mid-run overwrite (an isolated re-run passed 194/194), a Doctor's
cargo test --bin loom-daemon reported results for a binary that, per
strings, contained none of that PR's code, and a deliberately
behavior-flipped local canary build landed at the shared path while Judges
concurrently tested the real PR.
A shared-target-dir integration-test result is not verdict-bearing evidence. Treat a pass or a fail observed there as uninformative — not as grounds to approve, reject, or declare a fix confirmed — until you have reproduced it from an isolated build.
The recipe: the CARGO_TARGET_DIR Loom gave you
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.
- 27d ago Changed · +1 lines 2b6528324d08
- 1mo ago Changed · -6 lines ec62fec1f15b
- 1mo ago Changed f573d6684159
- 1mo ago First seen · 106 lines · 70 tokens per session scan C 05a96fcebcdc
loom-cargo-target-isolation is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,400 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
loom-cargo-target-isolation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| loom-cargo-target-isolationrjwalters/kicad-tools | Skill | 73 | yesterday | MIT | C | 70 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |