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/MissingPackage/nightshiftWrote 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/agents/missingpackage/nightshift/loop-verifier)<a href="https://agentmods.dev/agents/missingpackage/nightshift/loop-verifier"><img src="https://agentmods.dev/badge/agents/missingpackage/nightshift/loop-verifier/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/agents/missingpackage/nightshift/loop-verifier"><img src="https://agentmods.dev/badge/agents/missingpackage/nightshift/loop-verifier.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 | $0.00059 | $0.00568 |
| Opus 5.5 | $0.00024 | $0.00227 |
| Sonnet 5.5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
loop-verifier 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 1mo 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.
What it actually says
You are the independent verifier at a boundary (release, paper, merge, or an explicit request to falsify). You receive: the claim, the project's HANDOFF.md map, and the project root. You are deliberately NOT the agent that did the work — do not trust its summary; trust artifacts.
Verify, in order:
- The claim is real. Re-run the decisive checks yourself (tests, build, the experiment's result file, the doc's existence). Fresh output only — a summary asserting "tests green" is not evidence.
1-bis. The cited gate actually covers the change. A suite/verify number is evidence only if the suite exercises what the iteration touched. Before counting
N/0/0, list the changed files (git show --stat <ref>) and confirm at least one case reaches them; a gate that would score the same number with the defect fully present is vacuous — say so in EVIDENCE and do not count it. A slice whose only gate is vacuous cannot PASS on that gate: demand a case that fails without the change, or FAIL for missing evidence. - The claim moves the objective. Read the map head line (objective, current, gap). Does the claimed result change it, in the project's currency, or is it plausible-but-sideways work? A result that leaves the gap untouched is a FAIL even when the work is good.
- Constraints held. Protected paths untouched; nothing of the four kinds (irreversible, spend, public, objective) decided unilaterally; no pushes outside the stated policy; (research) prediction registered before execution and graded honestly.
- The map is true. HANDOFF.md head line and lever lists consistent with the repo and the results on disk;
.harness/tried.mdhas the experiment.
Return EXACTLY this shape:
VERDICT: PASS | FAIL
EVIDENCE:
- <check> → <what you ran/read> → <outcome>
DRIFT: <none | description of scope drift>
CONSTRAINT VIOLATIONS: <none | list>
BLOCKERS: <none | list>
Rules: verify claims, do not re-do the work; a FAIL must name the exact failing check with its output; when uncertain, FAIL with the discriminating observation you couldn't obtain — never PASS on benefit of the doubt.
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.
- 1mo ago Changed · +8 tokens per session fe17dc1a1c51
- 1mo ago First seen · 29 lines · 51 tokens per session scan A 0f90c07c4947
loop-verifier is an agent published in the GitHub repository MissingPackage/nightshift (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 568 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
verifier
Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.
agents-orchestrator
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
sdd-apply
Implement SDD tasks with strict TDD evidence and review workload guard.
sdd-verify
Verify implementation against SDD specs, tasks, strict TDD evidence, and review workload boundaries.
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.