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 tianhanz/ears --skill resumegit clone --depth 1 https://github.com/tianhanz/earsWrote 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/tianhanz/ears/resume)<a href="https://agentmods.dev/skills/tianhanz/ears/resume"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/resume/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/tianhanz/ears/resume"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/resume.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 | $0.00040 | $0.01424 |
| Opus 5 | $0.00020 | $0.00712 |
| Sonnet 5 | $0.00008 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Skill
Load and restore task state from a structured checkpoint file.
When to Use
- Session start: After context loss or session restart
- Crash recovery: Picking up after unexpected interruption
- Task handoff: Another person/agent continuing work
- Branch fork: Starting from another branch's checkpoint
- Manual resume: User explicitly requests
/resume [checkpoint-file]
Step 1 — Find checkpoint
If no argument provided: Find latest checkpoint on current branch:
BRANCH=$(git branch --show-current)
LATEST=$(ls -t .claude/checkpoints/${BRANCH}-*.yaml 2>/dev/null | head -1)
if [ -z "$LATEST" ]; then
echo "No checkpoint found for branch: $BRANCH"
echo "Available checkpoints:"
ls -t .claude/checkpoints/*.yaml 2>/dev/null | head -10
exit 1
fi
echo "Found checkpoint: $LATEST"
CHECKPOINT_FILE="$LATEST"
If argument provided: Use that checkpoint file or branch name:
ARG="$1"
if [ -f "$ARG" ]; then
CHECKPOINT_FILE="$ARG"
elif ls -t .claude/checkpoints/${ARG}-*.yaml 2>/dev/null | head -1 > /dev/null; then
CHECKPOINT_FILE=$(ls -t .claude/checkpoints/${ARG}-*.yaml | head -1)
else
echo "Checkpoint not found: $ARG"
exit 1
fi
Step 2 — Load and display checkpoint
import yaml
import os
checkpoint_file = os.environ.get('CHECKPOINT_FILE', '.claude/checkpoints/latest.yaml')
with open(checkpoint_file, 'r') as f:
checkpoint = yaml.safe_load(f)
print("=" * 60)
print(f"CHECKPOINT RESUME: {checkpoint_file}")
print(f"Created: {checkpoint['created_at']}")
print(f"Branch: {checkpoint['branch']}")
print("=" * 60)
print()
# Phase
phase = checkpoint.get('phase', {})
print("PHASE")
print(f" Current: {phase.get('current', '?')}")
print(f" Completed: {', '.join(phase.get('completed', []))}")
print(f" Next: {', '.join(phase.get('next', []))}")
print()
# Parameters
params = checkpoint.get('state', {}).get('parameters', [])
if params:
print(f"PARAMETERS ({len(params)} extracted)")
for p in params:
unit = p.get('unit', '')
print(f" {p['name']} = {p['value']} {unit} [{p.get('confidence','?')}] -- {p.get('source','?')}")
print()
# Experiments
experiments = checkpoint.get('state', {}).get('experiments', [])
if experiments:
print(f"EXPERIMENTS ({len(experiments)} total)")
for exp in experiments:
progress = f" {int(exp['progress']*100)}%" if 'progress' in exp else ""
reason = f" -- {exp['reason']}" if 'reason' in exp else ""
print(f" {exp['name']} [{exp['status']}]{progress}{reason}")
print()
# Decisions
decisions = checkpoint.get('state', {}).get('decisions', [])
if decisions:
print(f"DECISIONS ({len(decisions)} made)")
for dec in decisions:
print(f" {dec.get('question','?')} -> {dec.get('decision','?')} [{dec.get('confidence','?')}]")
print()
# Blockers
blockers = checkpoint.get('blockers', [])
if blockers:
print(f"BLOCKERS ({len(blockers)} open)")
for b in blockers:
assumption = f" (assuming: {b['assumption']})" if 'assumption' in b else ""
print(f" [{b.get('impact','?')}] {b['question']}{assumption}")
print()
# Artifacts — verify they exist
artifacts = checkpoint.get('artifacts', [])
if artifacts:
print(f"ARTIFACTS ({len(artifacts)} tracked)")
missing = 0
for a in artifacts:
path = a['path'].replace('~', os.path.expanduser('~'))
exists = os.path.exists(path)
status = "OK" if exists else "MISSING"
if not exists:
missing += 1
print(f" [{status}] {a['path']} ({a.get('role','?')})")
if missing > 0:
print(f"\n WARNING: {missing} artifact(s) missing!")
print()
# Resume instructions
print("=" * 60)
print("RESUME INSTRUCTIONS")
print("=" * 60)
print()
print(checkpoint.get('resume_instructions', '(no instructions)'))
print()
print("=" * 60)
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.
- 8d ago First seen · 181 lines · 40 tokens per session scan A 351f06e07827
resume is a skill published in the GitHub repository tianhanz/ears (5 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,424 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
testing-api-authentication-weaknesses
Tests API authentication mechanisms for weaknesses including broken token validation, missing authentication on endpoints, weak password policies, credential stuffing susceptibility, token leakage in URLs or logs, and session management flaws. The tester evaluates JWT implementation, API key handling, OAuth flows, and…
Effective Memory
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
s-compact
Session handoff for the next session — write-side pair of /s-continue. Triggers on "s-compact", "session handoff", "handoff prompt", "hand off", "wrap up the session", "prep for next session". Distills what /s-continue cannot recover: subagent findings, tool-output numbers, and decisions that never entered the…
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
start
Session initialization and lifecycle management: bootstraps session context, organizes files, generates CLAUDE.md, manages soul purpose lifecycle with completion protocol and active context harvesting. Use when user says /start, /init, bootstrap session, initialize session, or organize project.
test-spec-gen
Universal test specification generator that explores codebases, researches best practices, and generates comprehensive test specs via multi-agent orchestration. Outputs Hermes-style test specification documents with TC-XXX formatting, area segmentation, and optional Trello card conversion.