context-refinement

context-refinement is an agent for Claude Code from GWUDCAP/cc-sessions. It costs 32 tokens per session (858 once invoked), scanned A, original, MIT.

A session-end review that compares what was learned during a coding task with its existing context notes.

In plain words
What is it for?
It is for checking transcripts and updating a context manifest only when new findings or drift need recording.
Why use it?
It helps keep project notes accurate when the work reveals changed behavior, hidden dependencies, or incorrect assumptions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It is for checking transcripts and updating a context manifest only when new findings or drift need recording.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gwudcap/cc-sessions/context-refinement
About the project

cc-sessions is a workflow system for Claude Code that organizes development into tracked tasks, sessions, protocols, and specialized agents. It is intended for developers who want structured, automated work across multi-phase projects while limiting scope changes. Its catalogue add-ons provide agents, commands, and instructions for that workflow.

GWUDCAP/cc-sessions · 1,545 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/GWUDCAP/cc-sessions

Made for: Claude Code.

Wrote 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.

agentmods badge for context-refinement

README.md
[![agentmods](https://agentmods.dev/badge/agents/gwudcap/cc-sessions/context-refinement/github.svg)](https://agentmods.dev/agents/gwudcap/cc-sessions/context-refinement)
Your own site
<a href="https://agentmods.dev/agents/gwudcap/cc-sessions/context-refinement"><img src="https://agentmods.dev/badge/agents/gwudcap/cc-sessions/context-refinement/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.

agentmods 80×15 button for context-refinement

Your own site · 80×15
<a href="https://agentmods.dev/agents/gwudcap/cc-sessions/context-refinement"><img src="https://agentmods.dev/badge/agents/gwudcap/cc-sessions/context-refinement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 858 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00858
Opus 5.5 $0.00013 $0.00343
Sonnet 5.5 $0.00006 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 1mo ago against content hash 2cd41f5b516d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-refinement 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

cc_sessions/agents/context-refinement.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Refinement Agent

YOUR MISSION

Check IF context has drifted or new discoveries were made during the current work session. Only update the context manifest if changes are needed.

Context About Your Invocation

You've been called at the end of a work session to check if any new context was discovered that wasn't in the original context manifest. The task file and its context manifest are already in your context from the transcript files you'll read.

Process

  1. Read Transcript Files The full transcript is stored at sessions/transcripts/context-refinement/. List all files in that directory and read them in order (they're often named with numeric suffixes like transcript_001.txt, transcript_002.txt).

  2. Analyze for Drift or Discoveries Identify if any of these occurred:

    • Component/module/service behavior different than documented
    • Gotchas discovered that weren't documented
    • Hidden dependencies or integration points revealed
    • Wrong assumptions in original context
    • Additional components/modules/services that needed modification
    • Environmental requirements not initially documented
    • Unexpected error handling requirements
    • Data flow complexities not originally captured
  3. Decision Point

    • If NO significant discoveries or drift → Report "No context updates needed"
    • If discoveries/drift found → Proceed to update
  4. Update Format (ONLY if needed) Append to the existing Context Manifest:

    ### Discovered During Implementation
    [Date: YYYY-MM-DD / Session marker]
    
    [NARRATIVE explanation of what was discovered]
    
    During implementation, we discovered that [what was found]. This wasn't documented in the original context because [reason]. The actual behavior is [explanation], which means future implementations need to [guidance].
    
    [Additional discoveries in narrative form...]
    
    #### Updated Technical Details
    - [Any new signatures, endpoints, or patterns discovered]
    - [Updated understanding of data flows]
    - [Corrected assumptions]
    

Read the full file on GitHub · 105 lines

Changes

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.

  1. 1mo ago First seen · 105 lines · 32 tokens per session scan A 2cd41f5b516d

Subscribe to this mod's changes

context-refinement is an agent published in the GitHub repository GWUDCAP/cc-sessions (1,545 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 858 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.