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 serejaris/kimi-skills --skill interactive-research-report-engit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/interactive-research-report-en)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/interactive-research-report-en"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/interactive-research-report-en/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/serejaris/kimi-skills/interactive-research-report-en"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/interactive-research-report-en.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 | $0.00103 | $0.02549 |
| Opus 5 | $0.00051 | $0.01274 |
| Sonnet 5 | $0.00021 | $0.00510 |
| Haiku 4.5 | $0.00010 | $0.00255 |
Grade A, and why
interactive-research-report 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Research Report · site-building skill
Turn one deep report (any topic: chips, the hog cycle, energy, logistics, pharma…) into an interactive, drillable, animated-cover, editorial-grade single-page research site.
The skill has three layers: invariants (fonts/palette/layout/components — copy verbatim, see DESIGN.md and assets/), abstraction rules (covers generated from the "theme atom", charts selected by "data shape" — see COVER.md and CHARTS.md), and methodology (the debug loop and postmortem checklist — see QA.md).
0 · File map
| File | When to read |
|---|---|
DESIGN.md |
Read fully before starting — design-system hard constraints + editorial components + copy register |
CHARTS.md |
Consult before every chart — curated signature graphics, elimination list, and data-shape selection |
COVER.md |
When building the cover — four-state cover engine (incl. the D unboxing opener) + the "theme atom" abstraction |
QA.md |
After every module + before wrapping up — debug loop, gates, postmortem checklist |
assets/theme.css |
Copy directly as the site's css/style.css (base theme, use as-is) |
assets/fonts.css |
Copy directly (ET Book base64-inlined; external font links forbidden) |
templates/utils.js |
Copy directly as js/utils.js (canvas/drill-down/tooltip/frame skeleton) |
templates/skeleton.html |
Starting skeleton for the site |
templates/bundle.py |
Single-file bundling script (just edit the file manifest) |
references/gallery/ |
One finished screenshot per pattern — check the picture whenever unsure "what it should look like" |
references/BUILD_LOG-example.md |
Build log of a complete case (V1→V8.4), the why behind every decision |
1 · Input contract (confirm/collect with the user before starting)
- Prose fact source: one report md/pdf (the single source of truth; the website prose transcribes it faithfully, preserving hedged wording).
- Data tables: structured data (csv/json/tables all fine). You compile it into a
js/data.jsexposingwindow.RPT = { key: [...] }, with snake_case English keys. - Source register: source + date for every key number. Compile into
js/sources.js(a K1–Kn anchor table). Sources without dates must be graded (company primary > cross-check > broker relay > derived). - Theme atom (one question suffices): what is the most physical, decomposable, instantly recognizable entity in this industry? Chips = the package/die; hogs = the industrial farm; shipping = the container ship; power = the generating unit. All four cover states are different views of this same physical object. A recurses the object itself (draw the recognizable object directly, zooming out until it becomes one cell of a larger array of its kind) — not "some causal/mechanism logic" (that's a flowchart with a zoom slapped on, a classic failure). See COVER.md.
- Language (default: institutional research English, sentence case) and delivery width baseline (default: dual acceptance at 1680/1280).
What ships with it
38 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.
- agents/openai.yaml 316 B
- assets/fonts.css 174 KB
- assets/theme.css 20 KB
- CHARTS.md 33 KB
- COVER.md 12 KB
- DESIGN.md 6.6 KB
- QA.md 7.6 KB
- references/BUILD_LOG-example.md 4.6 KB
- references/gallery/component_quote.png 56 KB
- references/gallery/component_term_columns.png 93 KB
- references/gallery/cover_a_recursion.png 623 KB
- references/gallery/cover_b_realistic.png 307 KB
- references/gallery/cover_c_blueprint.png 243 KB
- references/gallery/cover_d_unbox.png 323 KB
- references/gallery/layout_rail.png 374 KB
- references/gallery/pattern_band_readout.png 160 KB
- references/gallery/pattern_comparison_matrix.png 150 KB
- references/gallery/pattern_destiny_flow.png 137 KB
- references/gallery/pattern_evidence_object.png 350 KB
- references/gallery/pattern_gate_ladder.png 81 KB
- references/gallery/pattern_generational_stacks.png 105 KB
- references/gallery/pattern_iso_towers.png 504 KB
- references/gallery/pattern_lifelines.png 132 KB
- references/gallery/pattern_odds_board.png 157 KB
- references/gallery/pattern_paired_bars.png 60 KB
- references/gallery/pattern_phase_orbit.png 298 KB
- references/gallery/pattern_scenario_chain.png 56 KB
- references/gallery/pattern_scrolly_tape.png 344 KB
- references/gallery/pattern_small_multiples_series.png 223 KB
- references/gallery/pattern_small_multiples.png 58 KB
- references/gallery/pattern_submerged_timeline.png 54 KB
- references/gallery/pattern_value_stack.png 123 KB
- references/gallery/pattern_verdict_scale.png 249 KB
- references/gallery/pattern_wallchart_timeline.png 81 KB
- references/gallery/pattern_waveform_chain.png 294 KB
- templates/bundle.py 1.7 KB runs code
- templates/skeleton.html 4.5 KB
- templates/utils.js 6.2 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.
- 9d ago First seen · 80 lines · 103 tokens per session scan A 190b6c894389
interactive-research-report is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 2,549 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 2026-09-03.
Other skills, from other repositories
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.