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 ur-grue/autopunk-media-skills --skill investigation-timeline-buildergit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/investigation-timeline-builder)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/investigation-timeline-builder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/investigation-timeline-builder/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/ur-grue/autopunk-media-skills/investigation-timeline-builder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/investigation-timeline-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 92 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00038 | $0.02650 |
| Opus 5.5 | $0.00015 | $0.01060 |
| Sonnet 5.5 | $0.00008 | $0.00530 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
investigation-timeline-builder 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigation Timeline Builder
What This Skill Does
Builds a structured, annotated chronological timeline from raw notes, documents, or source interview summaries, formatted for both internal reporting use and potential publication as a graphic.
When To Use This Skill
- You have accumulated research from multiple sources and need to impose chronological order on a complex sequence of events
- You are preparing a narrative investigation and need to see the full arc of events before structuring the story
- You want a timeline that flags gaps, contested dates, and unverified entries so editors can see what still needs reporting
- You are planning a published timeline graphic and need a draft with source attributions for each entry
What You Need To Provide
Required: Raw notes, document excerpts, or bullet-point summaries of events in any order; the investigation's subject (person, institution, or incident) Optional: Known key dates you want anchored; the intended output use (internal working document vs. publishable graphic); any disputed or uncertain dates you want flagged; sources for specific events (document names, interviewee names)
How the Assistant Approaches This
- Extracts all dateable events from the raw input and sorts them chronologically, noting where only approximate dates are available
- For each entry, records the event, the source or document it comes from, and a verification status (confirmed, single-source, or unverified)
- Identifies structural gaps in the timeline — periods of unexplained silence, missing transitions between events, or logical breaks that suggest something happened but is not yet documented
- Produces two versions if requested: a detailed internal version with source notes and verification flags, and a clean publishable version suitable for graphic design handoff
- After the timeline, provides a "Next Step" note: identifying the highest-priority reporting gap to close first, whether to run foia-request-writer to obtain official records for an unverified entry, and what is needed before the publishable version can be released
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.
- 1mo ago First seen · 148 lines · 38 tokens per session scan A a0a4fa9dcfb2
investigation-timeline-builder is a skill published in the GitHub repository ur-grue/autopunk-media-skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,650 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 2026-09-04.
Other skills, from other repositories
Litigation Chronology
Use when building a factual timeline for litigation from provided source documents, producing a structured chronology table with citations, disputed/undisputed flags, and gap analysis for attorney review.
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
entity-graph
Resolve entities across an investigation's documents into a Neo4j graph after a mandatory human review gate. Layer-2, operator-tier, Docker-gated -- run it to deduplicate people/orgs across the corpus, decide the "maybe" matches yourself, then write the resolved network to Neo4j for queryable analysis.
building-chronologies
Use when users say "build a chronology", "make a timeline", "what happened when", "chronology from disclosure", "source the key events", or need legal documents, correspondence, pleadings, witness evidence, or disclosure materials turned into a sourced event chronology.
analysis-recipe
This skill should be used when the user asks to "run the analysis recipe", "run the 13-point checklist", "run the per-source investigative pass", "analyze this FOIA/audit-log source for out-of-state / immigration / pretext / mega-users / co-travel", "roll up findings across multiple sources/agencies", or "test the…
ingest
This skill should be used when the user asks to "ingest a PDF / document", "extract text from a scanned PDF preserving page and bounding-box provenance", "convert a FOIA PDF to DoclingDocument keeping citations", "OCR a scanned document but decide native-text-vs-re-OCR first", "turn a PDF into provenance-preserving…