Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yonatangross/orchestkitnpx agentmods add skills/yonatangross/orchestkit/paired-probeWrote 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/yonatangross/orchestkit/paired-probe)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/paired-probe"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/paired-probe/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/yonatangross/orchestkit/paired-probe"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/paired-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.00966 |
| Opus 5.5 | $0.00040 | $0.00386 |
| Sonnet 5.5 | $0.00020 | $0.00193 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
paired-probe 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 25d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paired-probe
A check that prints the same thing whether or not the fault is present has measured nothing. It still returns an answer, that answer looks like evidence, and it gets acted on. This skill makes the blindness fail loudly instead.
When to reach for it
Before reporting any of these, because all of them are verdicts:
- "nothing found", "all clean", "no failures", "safe to delete"
- a sweep, audit, or status roll-up over N items
- a security or CI gate that just went green
- any check that passed when you expected it to fail
And immediately whenever a result surprises you by passing. Surprise is the cheapest available signal that the instrument, not the world, is what changed.
The three gates
| Gate | Question | Failure it catches |
|---|---|---|
| Differential | What does this print when the fault is ABSENT? | A probe that answers identically either way |
| Non-empty | How many items did it actually examine? | A sweep that measured zero and reported clean |
| Exit-aware | Did the probe itself run? | A swallowed error printing success |
Could-not-observe is a third outcome, never folded into either verdict.
Usage
# Differential: stage the fault, then remove it. Both arms must differ.
scripts/paired-probe.sh --name "retired model pin fails the gate" \
--present "printf 'model: claude-opus-4\n' > wf.yml && bash tests/ci/lint.sh" \
--absent "rm -f wf.yml && bash tests/ci/lint.sh"
# Single-shot, when the fault cannot be staged (a live sweep):
scripts/paired-probe.sh --name "worktrees examined" \
--measure "git worktree list --porcelain | awk '/^worktree /{print \$2}'" \
--min-count 1
Exit codes: 0 discriminates or met the count, 1 BLIND, 2 usage,
3 could-not-observe.
Why this exists
Four probes from a single session, 2026-08-21, each confidently wrong and none failing loudly. Three were caught by other people rather than by the check:
| The probe | What it asked | Why it lied |
|---|---|---|
| "is this branch pushed?" | the local ref cache | unfetched and never-pushed print identically |
| "is the branch on origin?" | the remote branch list | a squash-merge DELETES the head branch, so landed work reads as lost |
| "does this worktree hold unique work?" | diff main HEAD |
symmetric, so a stale tree flags main against itself |
| "any worktree at risk?" | a loop over a blocked temp file | the write failed, || true swallowed it, the loop read zero items and printed "safe to prune" |
What ships with it
1 file 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.
- 25d ago Changed · +1 lines a0bd71d7c88d
- 1mo ago Changed 800bb4b22dd5
- 1mo ago First seen · 85 lines · 100 tokens per session scan A f5aa060f219d
paired-probe is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 966 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.
examples-qa
Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…
simplifier
Replatform mode ("lift, tinker, and shift") — simplify a 1:1-lifted legacy system in place: modernize code and remove external dependencies, one pass at a time, each bracketed by characterization-tests replays, structure preserved. Owns the stack-neutral pass discipline; the transformation catalog and dependency…