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/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/commands/rjwalters/kicad-tools/cargo-target-isolation)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/cargo-target-isolation"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/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/commands/rjwalters/kicad-tools/cargo-target-isolation"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/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 | $0.00000 | $0.01158 |
| Opus 5.5 | $0.00000 | $0.00463 |
| Sonnet 5.5 | $0.00000 | $0.00232 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade C, and why
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 6d 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 — 86 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
Decide once, before your first verdict-bearing build:
-
$CARGO_TARGET_DIRis set to a Loom-owned dir: a path under<repo>/.loom/targets/, or the per-worktree dir named in your worktree's.loom-cargo-target-dir. Use it as given. Loom created it for this run and reclaims it (see Cleanup). Do not export another or delete it. -
Otherwise (unset, a shared cache, an operator value, or you are one of several agents building concurrently in one session, which all inherit the same value): build into your worktree's own
target/.CARGO_TARGET_DIR="$WORKTREE_ABS/target" cargo test -p loom-daemon --test the_test_you_need
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.
- 6d ago Changed · +1 lines 8629118cd961
- 9d ago Changed · -6 lines 9d6ae92ac09b
- 11d ago Changed 8feb89c7562b
- 23d ago First seen · 91 lines · 0 tokens per session scan C fd802f5eb045
cargo-target-isolation is a command published in the GitHub repository rjwalters/kicad-tools (70 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,158 tokens. 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.
Other commands, from other repositories
rust-test
Rust TDD workflow with unit and property tests.
check-production-ready
Verifies ccswarm's production quality criteria.
mutation-test
Uses cargo-mutants to run mutation tests and verify test quality.
check-impl
Runs basic checks on the ccswarm workspace.
cargo-bench
Command "cargo-bench" from olorehq/olore, covering cargo-bench(1), name, synopsis, description and working directory of benchmarks.
cargo-test
Command "cargo-test" from olorehq/olore, covering cargo-test(1), name, synopsis, description and documentation tests.