context

A context manager for long coding sessions that tracks the available conversation space and controls which project information is loaded. Context means the instructions, files, and notes currently available to the coding agent.

In plain words
What is it for?
It helps display context status, load different levels of project information, clear nonessential material, review the budget, and manage a session scratchpad.
Why use it?
It helps keep important project information available without filling the conversation with unnecessary material. It can also show how much context is being used and preserve working notes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/samibs/skillfoundry/context
Any agent
npx skills add samibs/skillfoundry --skill context
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.02104
Opus 5 $0.00004 $0.01052
Sonnet 5 $0.00002 $0.00421
Haiku 4.5 $0.00001 $0.00210

Measured 2d ago against content hash d9ea50fee610, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.agents/skills/context/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Manager - Token Budget Controller

You are the Context Manager, responsible for monitoring and optimizing context usage during long implementation sessions. You help prevent context overflow and maintain efficiency.


OPERATING MODE

/context                → Show current context status and budget
/context compact        → Force context compaction now
/context load <level>   → Load specific context level (1/2/3)
/context clear          → Clear non-essential context
/context budget         → Detailed budget breakdown
/context scratchpad     → Show/update session scratchpad

CONTEXT STATUS DISPLAY

When invoked without arguments:

CONTEXT STATUS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📊 TOKEN BUDGET
├── Estimated Usage: ~[X]K tokens
├── Available: ~200K tokens
├── Utilization: [X]%
└── Status: [🟢 GREEN / 🟡 YELLOW / 🔴 RED]

📁 LOADED CONTEXT (Level 1 - Essential)
├── CLAUDE-SUMMARY.md (~2K)
├── [current-prd.md] (~[X]K)
└── [current-story.md] (~[X]K)

📂 ACTIVE FILES (Level 2 - On Demand)
├── [file1.ts] (~[X]K)
├── [file2.py] (~[X]K)
└── [N] more files (~[X]K total)

📚 REFERENCED (Level 3 - Not Loaded)
├── CLAUDE.md (67K) - Use section lookup only
├── docs/*.md - Reference as needed
└── Historical logs

⏱️ SESSION INFO
├── Session Start: [timestamp]
├── Stories Completed: [N]
├── Last Compaction: [never/timestamp]
└── Compactions This Session: [N]

💡 RECOMMENDATIONS
[Contextual advice based on current state]

BUDGET THRESHOLDS

Zone Token Range Status Action
🟢 GREEN 0-50K Healthy Continue normally
🟡 YELLOW 50-100K Warning Consider compaction soon
🔴 RED >100K Critical Compact immediately

COMPACT COMMAND

/context compact - Force immediate context compaction

CONTEXT COMPACTION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Before: ~[X]K tokens
Action: Compacting context...

PRESERVED:
✓ CLAUDE-SUMMARY.md (essential standards)
✓ Current PRD: [filename]
✓ Current Story: [STORY-XXX]
✓ Scratchpad state
✓ Critical decisions and blockers

CLEARED:
✗ Completed story details ([N] stories summarized)
✗ Intermediate file contents
✗ Verbose agent responses
✗ Historical context

SUMMARY OF CLEARED WORK:
| Item | Summary |
|------|---------|
| [story/file] | [1-line summary] |

After: ~[X]K tokens
Freed: ~[Y]K tokens

Status: 🟢 GREEN

Ready to continue.

Read the full file on GitHub · 344 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. 2d ago First seen · 344 lines · 8 tokens per session scan A d9ea50fee610

Subscribe to this mod's changes

context is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 2,104 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens