manage-context-size

manage-context-size is a skill for Claude Code, Codex from broadinstitute/fiss-mcp. It costs 33 tokens per session (1,113 once invoked), scanned A, original, Apache-2.0.

Guidance for handling large Terra datasets, where Terra is a platform for managing genomic research data and workflows. It explains how to keep large metadata, logs, tables, and workflow results from overwhelming the AI's working context.

In plain words
What is it for?
Use it when working with many workflow shards, large entity tables, or verbose Cromwell workflow metadata and logs.
Why use it?
Large requests can return more text than the AI can safely process, causing important details to be lost or later instructions to be ignored.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when working with many workflow shards, large entity tables, or verbose Cromwell workflow metadata and logs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/broadinstitute/fiss-mcp/manage-context-size
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.

Any agent
npx skills add broadinstitute/fiss-mcp --skill manage-context-size
Clone the repo
git clone --depth 1 https://github.com/broadinstitute/fiss-mcp

Made for: Claude Code, Codex.

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 manage-context-size

README.md
[![agentmods](https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/manage-context-size/github.svg)](https://agentmods.dev/skills/broadinstitute/fiss-mcp/manage-context-size)
Your own site
<a href="https://agentmods.dev/skills/broadinstitute/fiss-mcp/manage-context-size"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/manage-context-size/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 manage-context-size

Your own site · 80×15
<a href="https://agentmods.dev/skills/broadinstitute/fiss-mcp/manage-context-size"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/manage-context-size.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,113 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 $0.00033 $0.01113
Opus 5 $0.00016 $0.00557
Sonnet 5 $0.00007 $0.00223
Haiku 4.5 $0.00003 $0.00111

Measured 11d ago against content hash 2a9a8ac2cf84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

manage-context-size 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 11d 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.

src/terra_mcp/skills/manage-context-size/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing Context Size

This skill teaches you how to avoid context exhaustion when working with large Terra datasets, scattered workflows, and verbose Cromwell metadata.

Context Size Risks

These operations can exhaust your context window:

Operation Risk Level Potential Size
get_job_metadata (full) CRITICAL 100K+ tokens per workflow
get_workflow_logs with many shards HIGH 25K+ tokens per task log
get_entities for large tables HIGH 10K+ tokens for 100 entities
get_submission_status with include_inputs=True MEDIUM 30K+ tokens for 9 workflows

Safe Patterns

1. Always Use Summary Mode for Metadata

# SAFE: Returns ~1-2K tokens
get_job_metadata(workspace_namespace, workspace_name, submission_id, workflow_id)

# DANGEROUS: Can return 100K+ tokens
# (There is no "full" mode - the tool protects you)

Summary mode is the default. It returns structured, actionable information without the verbose raw metadata.

2. Get Log URLs Before Fetching Content

For scattered workflows (50+ shards), fetching all logs can quickly exhaust context.

# Step 1: Get URLs only (fast, small response)
get_workflow_logs(
    workspace_namespace, workspace_name, submission_id, workflow_id,
    fetch_content=False  # Default
)

# Step 2: Identify which specific tasks failed
get_job_metadata(..., mode="summary")

# Step 3: Fetch content only for failed tasks you need
# (Consider fetching logs one at a time for scattered workflows)

3. Check Table Sizes Before Fetching Entities

# Step 1: Check row counts
get_workspace_data_tables(workspace_namespace, workspace_name)
# Response: {"tables": [{"name": "sample", "count": 5000}, ...]}

# Step 2: If count > 100, reconsider whether you need all entities
# Often, specific entity names from workflow inputs are sufficient

4. Limit Workflow Count in Submission Status

# Default: Returns first 10 workflows (manageable)
get_submission_status(workspace_namespace, workspace_name, submission_id)

# For large submissions, the default limit protects you
# Only use max_workflows=0 if you truly need all workflow details

Read the full file on GitHub · 139 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. 11d ago First seen · 139 lines · 33 tokens per session scan A 2a9a8ac2cf84

Subscribe to this mod's changes

manage-context-size is a skill published in the GitHub repository broadinstitute/fiss-mcp (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,113 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens