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 agentmods add skills/rjmurillo/ai-agents/checkpointnpx skills add rjmurillo/ai-agents --skill checkpointgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/checkpoint)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/checkpoint"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/checkpoint.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 | $0.00033 | $0.01757 |
| Opus 5 | $0.00016 | $0.00879 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade B, and why
checkpoint scanned grade B 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
allowed-tools: Bash(date:*), Bash(git branch:*), Bash(python3 -m json.tool:*), Bash(python3 scripts/redact_secrets.py:*), Glob, Read, Edit, Write How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint Command
Capture the current state of work as a durable, timestamped snapshot. Use this mid-session when you want a recoverable save point before a risky change, at the end of a working block, or whenever the user asks to "checkpoint" progress. The file is the human-readable record; the session log keeps a reference to it.
Optional label for this checkpoint: the problem statement from the conversation (under Copilot CLI the skill tool takes no argument vector, so state it in your message)
Triggers
| Trigger | Effect |
|---|---|
/checkpoint |
Write a timestamped checkpoint and link it from the active session log. |
/checkpoint label |
Write a labeled checkpoint and link it from the active session log. |
Process
Phase 1: Build checkpoint path
Resolve the timestamp, active session log, label, slug, and collision-safe checkpoint path.
Phase 2: Build and redact checkpoint
Render the checkpoint body and run it through the secret redactor before any Write call.
Phase 3: Persist and link
Write the redacted checkpoint to a path that does not already exist. Append checkpoint metadata to the active JSON session log when one exists, then validate the JSON.
Steps
-
Get the current UTC timestamp for the filename and the file body:
date -u +%Y%m%d-%H%M%SUse the output as
YYYYMMDD-HHMMSS. Also record the full ISO 8601 UTC time (date -u +%Y-%m-%dT%H:%M:%SZ) for the body. -
Identify the active session log and default label:
- Get the current branch with
git branch --show-current. - Find
.agents/sessions/*.jsonfiles and sort by filename descending. The filename order is the canonical "newest" order because session logs are named withYYYY-MM-DD-session-NN. - Read candidates in that order until you find the first log whose normalized
session.branchequals the current branch. Normalizesession.branchby trimming whitespace and removing one matching pair of surrounding backticks. That file is the active session log. - If
$ARGUMENTSis empty after trimming, derive the label from the active session log'ssession.objective. If no active session log exists, derive it from the current branch. If that is empty, usecheckpoint.
- Get the current branch with
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 First seen · 178 lines · 33 tokens per session scan B 9758770aa23e
checkpoint is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,757 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
extreme-router-refactor
Code refactoring, tech debt cleanup, and code review expertise for ExtremeRouter. Use when cleaning up code, fixing bugs, reviewing PRs, identifying tech debt, or when the user asks to "improve this code", "fix this mess", "why is this broken", "make this cleaner", or mentions code smells, duplication, or poor…
extremerouter-web-search
Web search via ExtremeRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.
extreme-router-code-audit
Mandatory critical-thinking and code-audit protocol for ExtremeRouter. Use on EVERY task that writes, modifies, adds, refactors, or fixes bugs in the codebase — including Per-Key Model Access Control, Playground, Health Monitor, Circuit Breaker, API routes, routing/middleware logic, or database schema. Also trigger…
code-review
Pre-commit code review using code-reviewer agent for bug detection, security analysis, and quality assurance. Manual invocation only. Use before git commits to catch issues early. Blocks commits on REQUESTCHANGES verdict.
debug
Systematic debugging using error-detective and debugger agents instead of manual investigation. Triggers automatically on: error, bug, broken, failing, exception, stack trace, test failure. Orchestrates RCA-first approach with parallel agent investigation.
deep-context
Build deep codebase understanding using Capsule context, progressive-reader, and specialist agents instead of overwhelming main context. Triggers on: don't have context, understand codebase, learn about, need background. Implements progressive context building.