Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Not-Diamond/self-care/plugin install self-careWrote 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/commands/not-diamond/self-care/autosync-tick)<a href="https://agentmods.dev/commands/not-diamond/self-care/autosync-tick"><img src="https://agentmods.dev/badge/commands/not-diamond/self-care/autosync-tick.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.01199 |
| Opus 5 | $0.00004 | $0.00600 |
| Sonnet 5 | $0.00002 | $0.00240 |
| Haiku 4.5 | $0.00001 | $0.00120 |
Grade A, and why
autosync-tick 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 6d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Care Autosync Tick
Run a single non-interactive autosync cycle.
This command is meant to be invoked by Claude Code scheduled tasks. Never ask the user any questions. Keep output concise and operational.
Do not use /self-care:run from here. It is interactive and includes remediation review. Reuse the same validator, trace-analyzer, and report-generator building blocks directly.
If $ARGUMENTS contains a project identifier from the scheduled task prompt, ignore it.
Step 1: Define Paths
CONFIG_PATH=".self-care/config.json"
STATE_PATH=".self-care/autosync.json"
AUTOSYNC_CLI="node "${CLAUDE_PLUGIN_ROOT}/lib/autosync.mjs""
Step 2: Poll Autosync State And Stage Work
Source .env first, then run:
if [ -f .env ]; then set -a && source .env && set +a; fi
node "${CLAUDE_PLUGIN_ROOT}/lib/autosync.mjs" tick --config "$CONFIG_PATH" --state "$STATE_PATH"
Parse the JSON output.
Step 3: Handle Non-Work States
If the status is one of the following, print one short line and stop:
config_missingdisabledlockednot_dueno_new_traces
If the status is error, output a short failure line that includes the message and stop.
Step 4: Process Each Staged Trace
Process result.traces in order. For each trace:
4a. Validate
Run:
node "${CLAUDE_PLUGIN_ROOT}/agents/tools/validate-trace.mjs" "<file_path>"
Parse the JSON output.
If validation fails:
- output a short failure line for that trace
- do not mark it complete
- continue to the next staged trace
4b. Analyze
Use the trace-analyzer agent to analyze the trace file at: <file_path>
Provide the agent with the validation context from 4a, including the format field so it applies the correct analysis strategy (OTEL: span-based analysis, Claude Code: event-based analysis). Also pass the pre-computed hash trace_hash so the analyzer skips re-hashing.
The trace-analyzer will run all 14 detection skills (2 deterministic tools + 12 interpretive skill agents) and return a reconciled JSON result. This is the same analysis pipeline used by /self-care:run.
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.
- 6d ago First seen · 164 lines · 8 tokens per session scan A 73dc95789cf6
autosync-tick is a command published in the GitHub repository Not-Diamond/self-care (28 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 1,199 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
optimize
Show TokenJam's savings/optimize report — where quota is going and what's recoverable. Equivalent to running tj optimize.
status
Show TokenJam's current status for every tracked agent — token usage, cost today, and active alerts. Equivalent to running tj status.
uninstall
Remove TokenJam's Claude Code integration — unwires the statusline, hooks, and OTel env vars that /onboard set up. Equivalent to running tj uninstall --yes. Does not remove the plugin itself.
doctor
Run TokenJam's health check — config, ingest endpoint, and storage. Equivalent to running tj doctor.
onboard
Set up TokenJam for this Claude Code install — wires the zero-token statusline, the resume-brief SessionStart hook, and local OTel telemetry ingest via the existing tj onboard command. Runs 100% locally, no signup.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.