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 panayiotism/claude-harness/plugin install claude-harnessWrote 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/panayiotism/claude-harness/checkpoint)<a href="https://agentmods.dev/skills/panayiotism/claude-harness/checkpoint"><img src="https://agentmods.dev/badge/skills/panayiotism/claude-harness/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/panayiotism/claude-harness/checkpoint"><img src="https://agentmods.dev/badge/skills/panayiotism/claude-harness/checkpoint.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 | $0.00058 | $0.03540 |
| Opus 5 | $0.00029 | $0.01770 |
| Sonnet 5 | $0.00012 | $0.00708 |
| Haiku 4.5 | $0.00006 | $0.00354 |
Grade A, and why
checkpoint 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 9d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint - Save Session Progress
Create a checkpoint of the current session: commit, push, PR, memory persistence, and feature archival.
Arguments: $ARGUMENTS
Session ID: ${CLAUDE_SESSION_ID} — session state lives in .claude-harness/sessions/${CLAUDE_SESSION_ID}/.
Phase 0: Set Paths
- Set path variables:
FEATURES_FILE=".claude-harness/features/active.json"ARCHIVE_FILE=".claude-harness/features/archive.json"MEMORY_DIR=".claude-harness/memory/"PROGRESS_FILE=".claude-harness/claude-progress.json"SESSION_DIR=".claude-harness/sessions/${CLAUDE_SESSION_ID}/"
Phase 1: Update Progress
- Update
${PROGRESS_FILE}with:- Summary of what was accomplished this session
- Any blockers encountered
- Recommended next steps
- Update lastUpdated timestamp
Phase 1.6: Persist to Memory Layers (OKF bundle)
Memory layers are an OKF v0.1 bundle at ${MEMORY_DIR}: one markdown concept file per entry with YAML frontmatter (required type field), plus an index.md listing per directory. See schemas/okf-memory.md for the format.
1.6. Persist session decisions to ${MEMORY_DIR}/decisions/:
- For each key decision made during this session:
- Write a concept file
dec-{NNN}-{slug}.md(next NNN from existing files; slug = lowercased decision, non-alphanumerics as hyphens, <=48 chars):--- type: Decision id: dec-{NNN} title: "{what was decided, <=80 chars}" timestamp: {ISO timestamp} feature: {feature-id} --- # {full decision text} ## Rationale {why this decision was made} ## Alternatives - {other options considered} ## Impact {files or areas affected} - Append
* [{id}: {title}](/decisions/{filename}) - {short description}to${MEMORY_DIR}/decisions/index.md
- Write a concept file
- Rolling window: if more than 50 decision concepts exist, delete the oldest files and their index lines (FIFO)
- Report: "Recorded {N} decisions to episodic memory"
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.
- 9d ago First seen · 337 lines · 58 tokens per session scan A d33c647d0362
checkpoint is a skill published in the GitHub repository panayiotism/claude-harness (79 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 3,540 once invoked, about $0.0003 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 skills, from other repositories
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
session-wrapup
End-of-session checkpoint — append diary, update active sprint doc with interim results/retro, write tech-lead handoff, commit and push. Use before /compact or at end-of-day. Distinct from sprint-wrap-up which closes a sprint.
catchup
Restore context after /clear by summarizing recent work and project state.
auto-git-commiter
Use when automatically commit and push OpenClaw changes to GitHub. Enable continuous improvement with automatic versioning, changelogs, and deployment-ready commits. Use when working with auto git commiter.
close
Close org-os session — summarize, write memory, commit, push.
project-context-sync
Keep a living project state document updated after each commit, so any agent (or future session) can instantly understand where things stand.