Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsnpx agentmods add skills/rjmurillo/ai-agents/checkpointWrote 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/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/rjmurillo/ai-agents/checkpoint"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00091 | $0.01227 |
| Opus 5.5 | $0.00036 | $0.00491 |
| Sonnet 5.5 | $0.00018 | $0.00245 |
| Haiku 4.5 | $0.00009 | $0.00123 |
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 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.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint
Migrated from the checkpoint command under ADR-064, which makes skills the single user-invocable surface. The command file is gone, so its path is named here in plain text rather than as a citation to something a reader could open.
The checkpoint and session directories
Resolve them the way paths.artifact_dir does, then take its checkpoints/ and
sessions/ subdirectories. Do not hard-code an agent-artifacts path: the tree
this skill writes into lives in the CONSUMER's workspace, and its root differs
between an upstream checkout and a plugin install. Every {checkpoints-dir} and
{sessions-dir} below means those resolved directories.
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.
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. |
Arguments
Optional label for this checkpoint: $ARGUMENTS
Process
Phase 1: Build checkpoint path
Resolve the timestamp, active session log, label, slug, and collision-safe checkpoint path.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +7 lines 0b6ba4bec0b3
- 1mo ago Changed · +3 lines cdbf26b4e016
- 1mo ago Changed · -74 lines · +58 tokens per session 0e4ce1e15cb5
- 1mo ago First seen · 178 lines · 33 tokens per session scan B 9758770aa23e
checkpoint is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,227 once invoked, about $0.0004 per session on Opus 5.5. 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
reuse-before-you-write
Use before writing any new function, helper, component or module - find what the repository, the standard library and the installed dependencies already provide, and use an established library instead of hand-rolled code for a non-trivial problem.
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
cowork-session
Claude Cowork shared AI pairing sessions with real-time sync, turn-taking, and collaboration context propagation.
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…