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 noah-hrbth/agent-tool-sync --skill roundtrip-checkgit clone --depth 1 https://github.com/noah-hrbth/agent-tool-syncWrote 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/noah-hrbth/agent-tool-sync/roundtrip-check)<a href="https://agentmods.dev/skills/noah-hrbth/agent-tool-sync/roundtrip-check"><img src="https://agentmods.dev/badge/skills/noah-hrbth/agent-tool-sync/roundtrip-check.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 | $0.00058 | $0.00984 |
| Opus 5 | $0.00029 | $0.00492 |
| Sonnet 5 | $0.00012 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
roundtrip-check 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roundtrip Check: Render → Adopt → Compare
Goal: prove that for every adapter where adopt.go claims a path is reversible, Render(canonical) → AdoptExternal(rendered_path) → reload canonical produces the same canonical entity bytes.
Procedure
Operate in a temp workspace — do not pollute examples/sandbox/ or the repo's .agentsync/.
1. Build a probe canonical
Create /tmp/agentsync-roundtrip/.agentsync/ with:
AGENTS.md— non-trivial multi-line content with code fences and unicode.rules/sample-rule.md— frontmatter (description,paths: [src/**/*.ts]) + body.skills/sample-skill/SKILL.md— frontmatter with every field set (name,description,allowed-tools,disable-model-invocation: true,paths).agents/sample-agent.md— frontmatter (name,description,tools,model: sonnet) + body.commands/sample-command.md— frontmatter (description,argument-hint,allowed-tools,model) + body.
The reserved name general must not appear — it will fail load.
2. Render via every adapter for both scopes
Write a small Go test (or a go run-able script under scripts/) that:
c, _ := canonical.Load(tmpWorkspace)
for _, a := range tools.All() {
for _, scope := range []tools.Scope{tools.ScopeProject, tools.ScopeUser} {
if !a.SupportsScope(scope).Supported { continue }
writes, _ := a.Render(c, scope)
for _, fw := range writes {
// write fw to disk under tmpWorkspace
}
}
}
3. Adopt every written path
For each fw.Path written above, call syncer.AdoptExternal(tmpWorkspace, fw.Path). Track which paths return errors — those are paths the adapter emits that adopt.go does not handle. Three valid outcomes:
- Adopted successfully — proceed to step 4.
- Adopted with the wrong canonical entity — bug in
adopt.gomatchers. - Returns "no canonical mapping for path" — either expected (concatenated rule bodies, alias files like
general.mdc→AGENTS.md) or a missing matcher. The adapter file should document which paths are intentionally non-reversible.
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 First seen · 88 lines · 58 tokens per session scan A b312d75d3ded
roundtrip-check is a skill published in the GitHub repository noah-hrbth/agent-tool-sync (2 stars, last pushed 16d ago), licensed MIT. It adds 58 tokens to every session and 984 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.