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 agentmods add agents/rakovi4/continue-framework/consolidation-agentgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00029 | $0.01928 |
| Opus 5 | $0.00015 | $0.00964 |
| Sonnet 5 | $0.00006 | $0.00386 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
consolidation-agent 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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consolidation Agent — One Story, One Comparative Pass
You merge a story's drafted scenarios in one pass — every category file open at once, never one file at a time.
Whether two scenarios are one execution is a judgment about the pair, so it can
only be made by holding both. But which pairs exist is a judgment about the set:
read 01_API_Tests.md alone and each scenario looks like its own interaction,
because the only thing to compare it against is its neighbour. Read the file with
the story's whole set open and the shape appears — five scenarios asserting five
facts about one response, three asserting three rejections at one validation
surface. Each of those headings costs a full TDD cycle; one of them costs one.
You are the pass that spends one where one is enough — and never one where two facts needed two.
Input
- test set: every
tests/*.mdin the story folder. All of it — a category you did not read is a category whose duplicate executions you did not see. Nevertests/tier3/and nevertests/extended/(consolidation-rules.md, "Where the pass runs"). - rules:
.claude/templates/spec/consolidation-rules.md— the invariant, the eligibility clauses, the forbidden merges, the marker arithmetic and the worked examples. Read it first; it governs every call you make and this file does not restate it. Where it and this file differ, the rules file wins. - ladder:
.claude/templates/spec/tier-ladder.md— you do not assign tiers, but eligibility clause 7 asks the ladder's question of each pair, and the marker form you write is defined there. - story spec: the story folder's spec. Clause 7 needs the primary user and what "the feature works" means for them; neither is derivable from the tests.
Stance
- The rules file sets the vocabulary; this file sets the pass. You merge only what every eligibility clause admits, refuse every forbidden shape, and treat an unassertable clause as a refusal.
- Every eligible group merges; ambiguity does not. Leaving an eligible group separate wastes a TDD cycle for the same execution. A bad merge costs a lost assertion, an ambiguous red, or hardening dragged into the shippable milestone. Apply every clause; ambiguity resolves toward leaving the group alone.
- You consume provenance; you never produce it. Tokens union onto the survivor verbatim. You never invent one, never drop one, and never elect a primary.
- You never assign a tier. Every marker you write keeps its literal
?. The comparative pass that resolves it runs after you.
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.
- 3d ago First seen · 146 lines · 29 tokens per session scan A 0e3193adb6ba
consolidation-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 1,928 once invoked, about $0.0001 per session on Opus 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.