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 OctoPerf/octoperf-claude-plugins --skill octoperf-report-item-editinggit clone --depth 1 https://github.com/OctoPerf/octoperf-claude-pluginsWrote 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/octoperf/octoperf-claude-plugins/octoperf-report-item-editing)<a href="https://agentmods.dev/skills/octoperf/octoperf-claude-plugins/octoperf-report-item-editing"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-report-item-editing/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/octoperf/octoperf-claude-plugins/octoperf-report-item-editing"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-report-item-editing.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 | $0.01200 |
| Opus 5 | $0.00000 | $0.00600 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
octoperf-report-item-editing 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing OctoPerf bench-report items
This skill covers changing the metrics/filters of a bench report item (a
BenchReportItem) — not reading its values (see octoperf://skills/bench-reports
for the read side). A report item's metrics are constrained: only certain sample
types, metric ids and tag filters are valid for a given report item type. The backend
exposes that contract; use it instead of guessing.
The model
A metric-bearing report item (StatisticTableReportItem, LineChartReportItem,
PercentilesChartReportItem, SummaryReportItem, PieChartReportItem,
StatisticTreeReportItem, BarChartReportItem, AreaRangeChartReportItem) holds a
list of ReportItemMetric:
id— theMetricId(e.g.RESPONSE_TIME_AVG,HITS_TOTAL).type— theSampleType(BASIC,WEB,LOAD,NUMBER_COUNTER, …).filters— a set ofSingleTermFilter{field,term}/MultiTermFilter{field,terms}narrowing the query by tag (region,injectorId,virtualUserName,actionPath,subSampleType, …). AND-combined.benchResultId,configs.
Which type/id/filter is legal depends on the report item type, the report's bench
results and whether it is a trend report. That is the allow-select descriptor.
Workflow
- Read the report —
get_bench_report(reportId)to see items and their ids/@type. - Resolve what's allowed —
get_report_item_allow_select(reportId, itemId)returns:sampleTypes— allowed sample types for the item.metricIdsBySampleType— selectable metric ids per sample type.tagKeyConstraints— per tag key: whether it's offered/required,allowedValues(a closed whitelist when non-empty, e.g.subSampleType∈ {Hit, Container}),single(single vs multi select), anddependsOn(parent keys, e.g.injectorIddepends onregion).
- Discover filter values (for open-ended tag keys):
get_report_tag_keys(reportId, sampleType)— the filterable tag keys.get_report_tag_values(reportId, sampleType, tagKeys, filters?)— the concrete values, optionally scoped by already-selectedfilters(e.g. restrictinjectorIdvalues to a chosenregionby passing{"region":["eu-west-1"]}).
- Build the metric(s) using only allowed types/ids/fields/values.
- Validate —
validate_report_item(reportId, itemId)returnsReportItemValidation(valid+violations). Fix every violation before persisting. - Persist —
patch_bench_report(reportId, patch)with an RFC 6902 JSON Patch (consultoctoperf://schema/bench-reportfor the item shape). The server runs the same allow-select validation as a pre-flight and rejects the patch (with the violation messages) if any metric is invalid, so a greenpatch_bench_reportmeans the edit was both structurally and semantically valid.
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.
- 12d ago First seen · 82 lines · 0 tokens per session scan A 3733076beec7
octoperf-report-item-editing is a skill published in the GitHub repository OctoPerf/octoperf-claude-plugins (0 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,200 tokens. 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
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail
Gmail: Send, read, and manage email.
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.