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 epicsagas/epic-harness --skill contextgit clone --depth 1 https://github.com/epicsagas/epic-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/epicsagas/epic-harness/context)<a href="https://agentmods.dev/skills/epicsagas/epic-harness/context"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/context/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/epicsagas/epic-harness/context"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00239 |
| Opus 5.5 | $0.00013 | $0.00096 |
| Sonnet 5.5 | $0.00007 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
context 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 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.
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
Context — Working-State Snapshot
Compaction timing belongs to the host (native auto-compaction; the harness already snapshots state on the PreCompact hook). This skill is about WHAT survives, not WHEN to compact.
Process
Before or during compaction, restate the working state in one block:
- Working on: [task description]
- Files modified: [explicit list]
- Status: [what's done, what remains]
- Key decisions: [important choices made, with why]
- Next step: [what to do after compaction]
Keep it terse — this block is what you (and the resume hook) reload after
compaction. Re-reading large files afterwards costs more than summarizing the
key facts beforehand.
Evidence Required
- Task, files, decisions, and next step all present in the summary block
- Snapshot written by the PreCompact hook (show file name if asked)
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 · -35 lines · -1 tokens per session 55f2e47764a0
- 1mo ago First seen · 67 lines · 34 tokens per session scan A 8d105f5710b1
context is a skill published in the GitHub repository epicsagas/epic-harness (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 33 tokens to every session and 239 once invoked, about $0.0001 per session on Opus 5.5. 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
recover-context
Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.
obsidian
Use the official Obsidian CLI (v1.12+) to manage vaults, notes, daily notes, search, tasks, tags, properties, links, templates, sync, publish, and workspaces. Use when the user mentions Obsidian, vaults, notes, or wants to automate note-taking and knowledge base workflows.
knowledge-session-state-and-context-active-turn-interactions-and-recovery
A session runtime component that coordinates the current task, user input, permissions, questions, and recovery after a crash or restart.
knowledge-session-state-and-context-compaction-pipeline-and-checkpoints
A context-compression component that reduces the conversation sent to the model when it approaches its input limit while keeping the full history stored.
knowledge-session-state-and-context-session-catalog-fork-rewind-and-export
A session-lifecycle component for finding, resuming, archiving, branching, rewinding, searching, and exporting saved conversations.
knowledge-session-state-and-context
A codebase guide for storing agent sessions, rebuilding their visible state, recovering active work, branching or rewinding history, and shortening context sent to the model.