hermes-webtop: Skill for Claude Code

.agents/skills/ci-log-capture/SKILL.md

ci-log-capture is a skill for Claude Code, Codex from gitricko/hermes-webtop. It costs 30 tokens per session (1,041 once invoked), scanned A, original, MIT.

A continuous-integration logging practice for saving command output to files instead of discarding it. Continuous integration, or CI, is the automated system that runs checks when code changes.

In plain words
What is it for?
Use it when changing shell-based tests or health checks so failures are captured, printed, and preserved by CI.
Why use it?
It prevents failed checks from showing only a vague error with no status, response body, or headers. Saved logs can be uploaded as build artifacts for later investigation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is gitricko/hermes-webtop's own configuration. It tells Claude Code and Codex how to work on hermes-webtop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hermes-webtop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gitricko/hermes-webtop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gitricko/hermes-webtop/main/.agents/skills/ci-log-capture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gitricko/hermes-webtop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ci-log-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/gitricko/hermes-webtop/ci-log-capture/github.svg)](https://agentmods.dev/skills/gitricko/hermes-webtop/ci-log-capture)
Your own site
<a href="https://agentmods.dev/skills/gitricko/hermes-webtop/ci-log-capture"><img src="https://agentmods.dev/badge/skills/gitricko/hermes-webtop/ci-log-capture/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.

agentmods 80×15 button for ci-log-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/gitricko/hermes-webtop/ci-log-capture"><img src="https://agentmods.dev/badge/skills/gitricko/hermes-webtop/ci-log-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01041
Opus 5.5 $0.00012 $0.00416
Sonnet 5.5 $0.00006 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 1mo ago against content hash 012142c93f47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ci-log-capture 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

if curl -sf https://api.example.com/health >/dev/null 2>&1; then
.agents/skills/ci-log-capture/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Log Capture — Replace /dev/null with Artifact Files

Every >/dev/null 2>&1 is a debug dead-end. Capture to files that auto-upload as CI artifacts so failures are self-documenting.

The problem

# BEFORE: failure body goes to void
if curl -sf https://api.example.com/health >/dev/null 2>&1; then
    echo "OK"
else
    echo "FAILED"  # but WHY? 400? 401? 500? timeout?
fi

When this fails in CI, you get "FAILED" with zero context. The HTTP status, response body, and headers are gone.

The pattern: run_and_log

# 1. Ensure log dir exists (matches workflow env)
CI_LOGS_DIR="${CI_LOGS_DIR:-/tmp/ci-logs}"
mkdir -p "${CI_LOGS_DIR}"

# 2. Helper: run command, capture to file, print on failure
run_and_log() {
    local test_name="$1"; shift
    local log_file="${CI_LOGS_DIR}/${test_name}.log"
    if "$@" >"${log_file}" 2>&1; then
        log_info "${test_name} — OK"
        return 0
    else
        log_error "${test_name} — FAILED (see ${log_file})"
        cat "${log_file}"   # immediate CI visibility
        return 1
    fi
}

# 3. Replace:
# BEFORE: if cmd >/dev/null 2>&1; then
# AFTER:  if run_and_log "endpoint-name" cmd; then

Artifact integration

The workflow must upload ${CI_LOGS_DIR} with if: always():

# .github/workflows/ci.yml
- name: Upload diagnostic logs
  if: always()
  uses: actions/upload-artifact@v7
  with:
    name: ci-logs-${{ github.run_id }}
    path: ${{ env.CI_LOGS_DIR }}/
    if-no-files-found: warn
    retention-days: 7

Name the log files so they sort logically in the artifact zip:

  • hermes-version.log
  • omniroute-models.log
  • ninerouter-chat.log
  • boot.log

Probe classification — what to capture vs keep silent

Probe type Capture? Notes
Version checks (--version) ✅ YES Confirms binary integrity
Health endpoints (/healthz) ✅ YES Shows HTTP status on failure
Model lists (/v1/models) ✅ YES Shows count + any error body
Chat completions ✅ YES Critical — shows 400/401/403 from upstream
Preconfig steps (login, setup) ✅ YES Shows which step failed
Cleanup (docker rm -f) NO — keep >/dev/null 2>&1 Expected noise
Container startup wait NO — keep >/dev/null 2>&1 Expected noise
Extension list (pi skill list) NO — keep stderr only Too verbose for artifacts

Read the full file on GitHub · 118 lines

Changes

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.

  1. 1mo ago First seen · 118 lines · 30 tokens per session scan A 012142c93f47

Subscribe to this mod's changes

ci-log-capture is a skill published in the GitHub repository gitricko/hermes-webtop (28 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,041 once invoked, about $0.0001 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 2026-10-05.

Related

ci-log-capture compared with skills from other repositories

ci-log-capture next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ci-log-capturegitricko/hermes-webtopSkill284d agoMITA30Claude Code, Codex
repair-github-ciTracer-Cloud/opensreSkill13kyesterdayApache-2.0A40Claude Code, Codex
mcore-create-issueNVIDIA/skillsSkill3.9kyesterdayApache-2.0A26Claude Code
debug-taskmoonrepo/moonSkill4.2kyesterdayMITA203Claude Code
operating-github-ci-fixerTracer-Cloud/opensreSkill13kyesterdayApache-2.0A48Claude Code, Codex
meta-long-running-build-watchdogopensquilla/opensquillaSkill7.1k6d agoApache-2.0A131Claude Code
analyze-cibenchflow-ai/skillsbenchSkill1.9k2d agoApache-2.0A15Claude Code