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.
git clone --depth 1 https://github.com/lx-wnk/Agent-ContextWrote 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/commands/lx-wnk/agent-context/discover)<a href="https://agentmods.dev/commands/lx-wnk/agent-context/discover"><img src="https://agentmods.dev/badge/commands/lx-wnk/agent-context/discover/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/commands/lx-wnk/agent-context/discover"><img src="https://agentmods.dev/badge/commands/lx-wnk/agent-context/discover.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 | $0.00016 | $0.00131 |
| Opus 5.5 | $0.00006 | $0.00052 |
| Sonnet 5.5 | $0.00003 | $0.00026 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
discover 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 20d 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
Run the Agent-Context discovery-map skill: read .agent-context/skills/discovery-map.md and follow it exactly to build — or, if .agent-context/map.json already exists, incrementally refresh — the map plus the per-node memory/map/<node>.md notes. Then check the size caps of the top map and every sub-map as .agent-context/skills/budget-check.md (section 2) describes.
The map stays on-demand: never load map.json or the node notes into always-on context.
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.
- 20d ago Changed 72fc75ccd976
- 22d ago Changed c6f81b59ff46
- 1mo ago First seen · 8 lines · 16 tokens per session scan A d55ec1f0a3b5
discover is a command published in the GitHub repository lx-wnk/Agent-Context (7 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 131 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 2026-08-31.
Other commands, from other repositories
compass-search
Search compass session-summary frontmatter (name, concept, type, drift, body) across all recorded sessions. Returns ranked hits with timestamps and drift glyphs.
compass-verify
Verify the Merkle hash chain over /.claude/projects/ /memory/ and report any tampered or missing files.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
story-continue
Resume an interrupted story from where you left off.
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.
unity-migrate
Plan and execute Unity version or render pipeline migration — identifies deprecated APIs, package compatibility, and executes migration steps.