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 Shweta-Mishra-ai/tokenmizer --skill checkpointgit clone --depth 1 https://github.com/Shweta-Mishra-ai/tokenmizerWrote 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/shweta-mishra-ai/tokenmizer/checkpoint)<a href="https://agentmods.dev/skills/shweta-mishra-ai/tokenmizer/checkpoint"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/checkpoint/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/shweta-mishra-ai/tokenmizer/checkpoint"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00434 |
| Opus 5 | $0.00030 | $0.00217 |
| Sonnet 5 | $0.00012 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
checkpoint scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "http://localhost:8000/api/checkpoint?session_id=$ARGUMENTS" \ What it actually says
Save the current session to TokenMizer graph memory.
What to do
- Ask the user for a session ID if not provided (suggest a slug based on what you're working on, e.g. "auth-service", "data-pipeline", "my-project")
- Call the TokenMizer checkpoint API:
curl -s -X POST "http://localhost:8000/api/checkpoint?session_id=$ARGUMENTS" \
-H "Content-Type: application/json"
- Show the user what was saved:
- Checkpoint ID
- Number of nodes in graph
- Resume token count
- The resume context block
If TokenMizer is not running
Tell the user to start it first:
tokenmizer serve
# or
python3 -m tokenmizer.api.app
Session ID rules
- Use lowercase slugs:
auth-servicenotAuth Service - Keep it short and meaningful
- Same ID across sessions for the same project
Example output to show user
✅ Session 'auth-service' saved
Checkpoint: ckpt_a3f9b2
Nodes: 14 (6 tasks, 4 decisions, 3 files, 1 error)
Resume size: 247 tokens
Resume context:
Goal: Build FastAPI auth service with JWT
Done: Project setup | User model | Login endpoint | Fix 422
In progress: Refresh token rotation
Decided: PostgreSQL | bcrypt | Redis for tokens
Files: api/auth.py, api/models.py, config.py
Continue: Implement token refresh endpoint
If $ARGUMENTS is empty, ask: "What should I call this session? (e.g. my-project)"
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.
- 10d ago First seen · 57 lines · 61 tokens per session scan A 5acc48674331
checkpoint is a skill published in the GitHub repository Shweta-Mishra-ai/tokenmizer (30 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 434 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
session-log
USE WHEN ending a substantial working session — user says "thanks/tomorrow/wrap up", or session shipped 3+ commits with no log today, or user asks for a summary. Distills the conversation into docs/sessions/YYYY-MM-DD- .md (context, what was done, key decisions, open questions, next steps). Hard cap 80 lines.…
pickup
Resume work on this project after an interruption or at the start of a new session: show recent wins, what was being done, the next action, and open decisions, in that order, then stop. Trigger only on an explicit /squirrel:pickup invocation, or an explicit request to resume or pick up this project's past work at the…
stash
Record one durable memory in the user's cross-project hoard: a correction, a decision with its reasoning, a bug and its fix, or a fact worth keeping. Only for an explicit /squirrel:stash invocation.
claude-bridge-role-memory-keeper
Playbook for a Claude Code agent in the dedicated memory keeper role — single-writer for shared agent memory across a team of 3+ peers. Use when you are designated as the keeper (= other peers send you write candidates, you write them and watch for drift). Memory hygiene + reconciliation against the canon + drift…
memory-loop-setup
Bootstrap the memory loop into any repo or Obsidian vault. Triggers: (1) "set up the memory loop / second brain / warm layer here" or "install this structure in another repo/vault", (2) a new project asking "make the AI remember across sessions and surfaces".