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 vasuag09/harness-claude --skill save-sessiongit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/save-session)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/save-session"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/save-session.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 | $0.00048 | $0.00324 |
| Opus 5 | $0.00024 | $0.00162 |
| Sonnet 5 | $0.00010 | $0.00065 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
save-session 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 8d 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.
What it actually says
/save-session — persist progress
Goal: a future session (or a fresh context) can pick up exactly where this left off.
File location
- Inside a git repo:
.claude/sessions/<YYYY-MM-DD>.md(append across the day). - Otherwise:
~/.claude/harness-claude/sessions/<YYYY-MM-DD>.md.
Create the directory if needed. Append to today's file; don't pollute it with old work — start a new dated file per day.
What to write (evidence-based, not aspirational)
# Session <date> — <project/feature>
## Goal / current objective
## What works (verified, with evidence: test names, commands, screenshots)
## What was tried and did NOT work (so we don't repeat it)
## Not yet attempted / remaining (the next concrete steps)
## Key decisions & files touched
## Open questions / blockers
How
- Summarize honestly: distinguish verified from assumed.
- Append (don't overwrite) under a timestamped subheading.
- Tell the user the file path so they can review/edit it.
This skill is also invoked automatically by the PreCompact and Stop hooks — keep the format stable so those writes stay consistent.
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.
- 8d ago First seen · 35 lines · 48 tokens per session scan A 189e470d6a35
save-session is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 324 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
catchup
Restore context after /clear by summarizing recent work and project state.
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
handoff
End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode).
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
consolidate
Audit and prune rules/skills/learnings to prevent context bloat. Triggers "consolidate", "clean up rules", "spa day", "what's redundant", degraded agent perf.