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 resume-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/resume-session)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/resume-session"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/resume-session/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/vasuag09/harness-claude/resume-session"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/resume-session.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 | $0.00036 | $0.00459 |
| Opus 5 | $0.00018 | $0.00230 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
resume-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 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.
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
/resume-session — pick up where you left off
Goal: restore working context cheaply, without re-exploring.
Do this
- Read the STATE spine first —
.claude/STATE.md(schema:docs/state-and-artifacts.md). Its frontmatter gives the machine-navigable position in one read:phase,status,slug,next_skill. If aslugis set, glance at.claude/planning/<slug>/(SPEC.md/PLAN.md/VERIFICATION.md) for the current artifacts. If STATE.md is absent, skip to the session file — the spine is optional. - Find the latest session narrative for the human story:
.claude/sessions/in the repo, else~/.claude/harness-claude/sessions/.- Pick the most recent by date; offer the user the last few if several exist.
- Read it and restate: the objective, what's verified-working, what failed (avoid repeating those dead ends), and the concrete next steps.
- Re-orient against current reality: confirm the repo state still matches (branch, key
files). If STATE.md and the session narrative disagree (e.g.
next_skillsays/harness-claude:implementbut the narrative describes shipping), flag the drift and reconcile from the repo — do not trust either blindly. - Propose the immediate next action (prefer STATE's
next_skill, cross-checked against the narrative's "remaining"), and confirm with the user.
Note
The SessionStart hook already surfaces STATE's next_skill (or a pointer to the latest
session file) automatically; this skill is the full, deliberate restore. Treat every file
as what was true when written — verify before trusting specifics (files/flags may have
changed).
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 · 33 lines · 36 tokens per session scan A 7c5626771f11
resume-session is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 459 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).
consolidate
Audit and prune rules/skills/learnings to prevent context bloat. Triggers "consolidate", "clean up rules", "spa day", "what's redundant", degraded agent perf.
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.