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 dashaworks/report-skills --skill report-publishergit clone --depth 1 https://github.com/dashaworks/report-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/dashaworks/report-skills/report-publisher)<a href="https://agentmods.dev/skills/dashaworks/report-skills/report-publisher"><img src="https://agentmods.dev/badge/skills/dashaworks/report-skills/report-publisher/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/dashaworks/report-skills/report-publisher"><img src="https://agentmods.dev/badge/skills/dashaworks/report-skills/report-publisher.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 | $0.00104 | $0.00587 |
| Opus 5 | $0.00052 | $0.00293 |
| Sonnet 5 | $0.00021 | $0.00117 |
| Haiku 4.5 | $0.00010 | $0.00059 |
Grade A, and why
report-publisher 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Publisher
The default "get it out of the chat" skill: whatever was just produced — deep research, a competitive analysis, a technical write-up — becomes a live web report with a URL worth sharing.
Follow the shared flow in the root SKILL.md (access check → get_design_system → author → lint_document → approval → publish). This file covers only what's specific.
When to use
- The user finished a research/analysis task and says "publish this", "make this a report", "make this shareable", "I want to send this to someone"
- Long markdown output that deserves better than a chat scroll or a raw gist
- The user wants a link, not a file
Steps
- Scope the content. Confirm what goes in (the whole conversation output? just the final analysis?) and the audience (colleague, community, public). Audience decides tone of the framing, not the facts. If it's for the team rather than the world and the user is in a team workspace (
account_status→org_kind: team), publish withvisibility: "team"so only signed-in org members can view it. - Structure for the web, don't paste. Reshape chat-formatted output into a real document: a title that states the finding, an executive summary up top, sections with descriptive headings, data moved into tables/charts where the design system provides them, sources/appendix at the end. Cut conversational scaffolding ("as we discussed above…").
- Author + lint + approval gate per the shared flow. In the preview, include your suggested title — titles that state the conclusion travel better than topic labels ("X is 30% cheaper than Y at scale", not "X vs Y comparison").
- Publish and hand over the URL. Mention the page is tracked: "ask me later how it's doing" (
get_analytics).
Hard rules
- Preserve the substance exactly — restructuring is allowed, changing findings, numbers, or hedges is not.
- Keep the user's citations/sources; a published report without its sources is a downgrade, not an upgrade.
- If content contains third-party confidential material (client names in research, quoted private messages), flag it at the approval gate.
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 · 30 lines · 104 tokens per session scan A b440181b0d9d
report-publisher is a skill published in the GitHub repository dashaworks/report-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 587 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.