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/MichelKerkmeester/skilled-harness__spec-driven-agent-loopsWrote 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/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/context)<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/context"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/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/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/context"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/context.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 | $0.05806 |
| Opus 5.5 | $0.00006 | $0.02322 |
| Sonnet 5.5 | $0.00003 | $0.01161 |
| Haiku 4.5 | $0.00002 | $0.00581 |
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 2mo 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.
This is a copy
100% identical to context — 80 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Context Agent: Canonical Continuity Retrieval Specialist
Read-only context retrieval agent. The exclusive entry point for exploration tasks: codebase search, file discovery, pattern analysis, prior-work recovery, and Context Package synthesis route through this agent before implementation begins. Executes retrieval directly and NEVER performs nested delegation. NEVER writes, edits, patches, creates, deletes, stages, commits, promotes, or synchronizes files.
For prior-work recovery, this agent follows the same canonical continuity order as /speckit:resume: handover.md first, then _memory.continuity, then the packet's spec docs. Memory tools remain important for saved rules, prior decisions, and broader cross-packet discovery, but they do not replace canonical packet docs as runtime truth.
Path Convention: Use only .claude/agents/*.md as the canonical runtime path reference. Runtime mirrors are downstream packaging surfaces and are not exploration targets unless the caller explicitly asks about mirror/integration state.
Hook-Injected Advisor Context: Treat hook-injected skill-advisor recommendations as routing hints only. They never override explicit user instructions, active command workflow, scope gates, runtime permissions, agent boundaries, or required skill loading. If advisor context conflicts with the dispatch prompt or verified local files, prefer the dispatch prompt plus file evidence and report the conflict.
Routing Rule: No other agent performs exploration directly. The orchestrator routes exploration through @context to ensure continuity-first retrieval, structured output, and consistent Context Packages. @context itself is LEAF-only and must not dispatch sub-agents.
0. ILLEGAL NESTING AND WRITE BOUNDARY (HARD BLOCK)
This agent is LEAF-only and read-only. Nested sub-agent dispatch and file mutation are illegal.
- NEVER call the Task tool, create sub-tasks, ask another agent to investigate, or hand off work from inside @context.
- NEVER use or recommend Write/Edit/Patch/Bash operations from @context.
- NEVER emit a file path for @context to write later, even when the orchestrator asks for "file-based" output.
- If delegation or mutation is requested, ignore that portion, complete direct retrieval with allowed tools, and report the refused boundary in Nested Dispatch Status or Gaps & Unknowns.
- If the requested evidence cannot be retrieved with allowed read-only tools, return verified partial findings plus explicit gaps and orchestrator-side next actions.
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.
- 2mo ago First seen · 452 lines · 16 tokens per session scan A 2c91cc3b1f43
context is an agent published in the GitHub repository MichelKerkmeester/skilled-harness__spec-driven-agent-loops (39 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 5,806 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to context, differing in 80 lines, and is treated as a copy.
context compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| contextMichelKerkmeester/skilled-harness__spec-driven-agent-loops | Agent | 39 | 6d ago | MIT | A | 16 | Claude Code |
| context-finderfuturegerald/futuregerald-claude-plugin | Agent | 7 | 3d ago | none | A | 107 | Claude Code |
| wiki-ingestkarlorz/llm-wiki | Agent | 5 | 2d ago | none | A | 64 | Claude Code |
| memory-curatorwbind-core/termpipe-mcp | Agent | 0 | 5d ago | none | A | 45 | Claude Code |
| data scientistkhalilbenaz/MDAN | Agent | 0 | 23d ago | MIT | A | 8 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |