AgentsView is a local application that collects coding-agent sessions into a searchable database and web interface, including usage and cost statistics. Developers use it to browse, analyze, and track sessions from Claude Code, Codex, and other supported agents, while the catalogue add-ons help operate it.
Borrowing it
Nothing to install: this file belongs to kenn-io/agentsview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kenn-io/agentsview/main/.agents/skills/sync-harness-icons/SKILL.mdgit clone --depth 1 https://github.com/kenn-io/agentsviewWrote 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/kenn-io/agentsview/sync-harness-icons)<a href="https://agentmods.dev/skills/kenn-io/agentsview/sync-harness-icons"><img src="https://agentmods.dev/badge/skills/kenn-io/agentsview/sync-harness-icons/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/kenn-io/agentsview/sync-harness-icons"><img src="https://agentmods.dev/badge/skills/kenn-io/agentsview/sync-harness-icons.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 | $0.00061 | $0.02663 |
| Opus 5.5 | $0.00024 | $0.01065 |
| Sonnet 5.5 | $0.00012 | $0.00533 |
| Haiku 4.5 | $0.00006 | $0.00266 |
Grade A, and why
sync-harness-icons scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -L`). The `/api/icon?pluginId=` endpoint returns 403. How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Harness Icons
Every harness AgentsView can read gets a monochrome brand mark in two places:
the "Every agent" chip grid in docs/website/index.html, and the HarnessIcon
component in the kit-ui repository that Forge draws in its launch and terminal
surfaces. New parsers land without either, so a person runs this skill after a
batch of provider additions to bring both back in sync, then moves the Forge pin
so Forge picks the marks up. Do the steps in order; each pull request references
the one before it.
1. Audit
From the AgentsView repository root, with a kit-ui checkout that is on main
and up to date (git -C <kit-ui> status -sb shows ## main...origin/main):
python3 .agents/skills/sync-harness-icons/audit.py --kit-ui <kit-ui checkout>
The script reads the provider headings in
docs/internal/session-format-sources.md, so a new parser is invisible to the
audit until its heading and evidence entry exist there; confirm that first. It
reports:
- chips that still use a two-letter text tag. Each is a sourcing target for step
2; a vendor may have published a logo since the last run. When a sourcing pass
finds nothing, add the chip to
TEXT_TAG_ACCEPTEDin the script with the month and what was searched, so later runs skip it until someone has a new lead. - providers with no landing-grid chip, matched by normalized name against the
chip list. Judge each line. Importers and IDE/CLI variants of a brand already
on the grid stay off it; add such keys to
INTENTIONALLY_UNLISTEDin the script with the reason. A provider the matcher missed because its chip has a different display name (codebuddyis the CodeBuddy CN chip) goes inCHIP_NAMES. Everything else needs a mark. - sprite symbols with no kit-ui id, which is the kit-ui gap list.
- chips whose name appears in no kit-ui
agentslist. A chip listed inTEXT_TAG_ACCEPTEDis expected here and needs no action.
2. Source a mark for each missing harness
Dispatch one subagent per three or four harnesses with this brief, writing to a scratch directory outside any repository:
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.
- yesterday Changed · +33 lines c1b1aa5360f7
- 28d ago First seen · 157 lines · 61 tokens per session scan A 421106dc336c
sync-harness-icons is a skill published in the GitHub repository kenn-io/agentsview (6,121 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 2,663 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.