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 FlowRegSuite/flowreg-agent-skills --skill flowreg-qc-and-auditgit clone --depth 1 https://github.com/FlowRegSuite/flowreg-agent-skillsWrote 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/flowregsuite/flowreg-agent-skills/flowreg-qc-and-audit)<a href="https://agentmods.dev/skills/flowregsuite/flowreg-agent-skills/flowreg-qc-and-audit"><img src="https://agentmods.dev/badge/skills/flowregsuite/flowreg-agent-skills/flowreg-qc-and-audit/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/flowregsuite/flowreg-agent-skills/flowreg-qc-and-audit"><img src="https://agentmods.dev/badge/skills/flowregsuite/flowreg-agent-skills/flowreg-qc-and-audit.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 | $0.00074 | $0.01980 |
| Opus 5 | $0.00037 | $0.00990 |
| Sonnet 5 | $0.00015 | $0.00396 |
| Haiku 4.5 | $0.00007 | $0.00198 |
Grade A, and why
flowreg-qc-and-audit 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 11d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality control and provenance audit
1. Purpose
Decide whether a completed run actually produced a scientifically usable result, and whether the record of it is complete enough for someone else to trust and reproduce.
A zero exit code is not a result. Neither is a corrected video that looks smoother.
2. Use this skill when
- Any registration run has finished — this skill is required after every executable workflow.
- Corrected data and a displacement field exist and need assessment.
- A run must be audited for provenance completeness or reproducibility.
- Someone claims a correction worked and you need evidence either way.
3. Do not use this skill when
- You are choosing a workflow or parameters →
flowreg-plan. - You are executing a run → the relevant execution skill.
- You are performing scientific motion analysis for its own sake — drift trajectories, deformation
measurement, magnification. That is the
analyze-motioncapability, which ships no skill in this release. Correction QC and motion science are different questions; do not conflate them.
4. Required inputs
- The run directory, including the manifest and the resolved configuration.
- The corrected output and, wherever it exists, the dense displacement field.
- Access to the original recording, read-only, for before/after comparison.
- The valid mask,
statistics.npzand the z-shift field where the workflow produced them. - The plan, so the QC gates it declared can actually be evaluated.
If the displacement field was not saved, say so plainly: most of the checks below become
not-assessable, and that is a materially weaker result than a pass.
5. Preflight checks
- Read
references/runtime-capability.mdfor each capability's conventions and output names. - Confirm which capability produced the run; the applicable checks differ (section 7).
- Confirm the manifest exists and parses. A run without a manifest cannot be audited, only inspected.
- Confirm the original data are reachable read-only. Never write to them.
What ships with it
9 files 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.
- assets/report-template.md 2.4 KB
- assets/schemas/qc-report.schema.json 4.4 KB
- assets/schemas/README.md 553 B
- assets/schemas/run-manifest.schema.json 9.5 KB
- assets/schemas/run-plan.schema.json 10 KB
- references/metrics.md 6.8 KB
- references/runtime-capability.md 18 KB
- scripts/qc_displacement.py 11 KB runs code
- scripts/validate_artifact.py 5.8 KB runs code
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.
- 11d ago First seen · 162 lines · 74 tokens per session scan A 41cf5d7f040f
flowreg-qc-and-audit is a skill published in the GitHub repository FlowRegSuite/flowreg-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,980 once invoked, about $0.0004 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…