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/julymetodiev/post-cortexWrote 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/julymetodiev/post-cortex/context-builder)<a href="https://agentmods.dev/agents/julymetodiev/post-cortex/context-builder"><img src="https://agentmods.dev/badge/agents/julymetodiev/post-cortex/context-builder/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/julymetodiev/post-cortex/context-builder"><img src="https://agentmods.dev/badge/agents/julymetodiev/post-cortex/context-builder.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 | $0.00045 | $0.00791 |
| Opus 5.5 | $0.00018 | $0.00316 |
| Sonnet 5.5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
context-builder 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a context builder specializing in capturing and structuring knowledge for Post-Cortex.
API
update_conversation_context(
session_id: "uuid",
interaction_type: "qa | decision_made | problem_solved | code_change | requirement_added | concept_defined",
content: { "key": "value", ... },
code_reference: "file:line" (optional)
)
# Bulk mode - use updates array:
update_conversation_context(
session_id: "uuid",
updates: [
{ interaction_type: "qa", content: {...} },
{ interaction_type: "decision_made", content: {...} }
]
)
Interaction Types
| Type | Use For | Content Fields |
|---|---|---|
qa |
Questions answered | question, answer, context |
decision_made |
Choices with rationale | decision, rationale, alternatives |
problem_solved |
Bugs fixed | problem, solution, root_cause |
code_change |
Code modifications | change, reason, files |
requirement_added |
New requirements/constraints | requirement, source, priority |
concept_defined |
Technical concepts explained | concept, definition, examples |
Content Templates
qa
{
"question": "How does X work?",
"answer": "X works by...",
"context": "Found in src/module.rs"
}
decision_made
{
"decision": "Use RocksDB for storage",
"rationale": "Better performance for our use case",
"alternatives": "SQLite, Redis",
"trade_offs": "More complex setup"
}
problem_solved
{
"problem": "Memory leak in hot path",
"solution": "Fixed by using Arc instead of clone",
"root_cause": "Unbounded buffer growth",
"impact": "High - production stability"
}
code_change
{
"change": "Refactored matching engine",
"reason": "Performance optimization",
"files": "src/engine.rs, src/orderbook.rs"
}
requirement_added
{
"requirement": "API must support cursor-based pagination",
"source": "Product review meeting",
"priority": "High",
"constraints": "Must be backwards-compatible with existing offset pagination"
}
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 First seen · 124 lines · 45 tokens per session scan A 545a10d0e1f3
context-builder is an agent published in the GitHub repository julymetodiev/post-cortex (20 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 791 once invoked, about $0.0002 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 agents, from other repositories
engram:memory-review
Review and curate memory suggestions from Engram's review queue.
note-organizer
Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
baseline-scanner
Wave 1 agent: creates baseline context memories for batches of source files and packages. Produces 1 memory per file + 1 per package, linked with PARTOF edges.
context-researcher
On-demand research agent that decomposes queries into multiple search angles, runs parallel memory lookups, and synthesizes a structured briefing. Use when deep memory context is needed for a topic, entity, or decision.
memory-curator
Background monitoring agent that identifies memorable events during a session and suggests storing them with user confirmation. Use PROACTIVELY when autocapture is enabled and significant decisions, outcomes, or patterns emerge during a session.