context-management

A guide for preserving important decisions and progress during long coding-agent tasks, especially when the conversation may be shortened or split across sessions.

In plain words
What is it for?
Recording plans, implementation progress, and evaluation notes in a persistent context file.
Why use it?
It reduces the chance that earlier decisions or unfinished work are forgotten when the agent’s context is limited.

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/jeremydev87/codingbuddy/context-management
Any agent
npx skills add JeremyDev87/codingbuddy --skill context-management
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/codingbuddy

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,410 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 $0.00038 $0.01410
Opus 5 $0.00019 $0.00705
Sonnet 5 $0.00008 $0.00282
Haiku 4.5 $0.00004 $0.00141

Measured 2d ago against content hash b0699d2d728a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-management 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.

packages/rules/.ai-rules/skills/context-management/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Management

Overview

AI assistant context windows are finite. Long tasks get compacted, earlier decisions are forgotten, and continuity breaks. Context management is the practice of preserving critical information so work survives compaction.

Core principle: If it matters after the current conversation, write it down. Memory is the enemy of continuity.

Iron Law:

EXTERNAL STATE > INTERNAL MEMORY
Write decisions to files. Files survive compaction; conversation memory does not.

When to Use

  • Starting a task that will span multiple sessions
  • Beginning PLAN mode (decisions must survive to ACT)
  • Completing ACT mode (progress must survive to EVAL)
  • When conversation is approaching context limits
  • Before any context compaction event
  • When resuming work after a break

The Context Document (codingbuddy)

The primary context persistence mechanism is docs/codingbuddy/context.md.

docs/codingbuddy/context.md
─────────────────────────────
This file is:
- Created/reset by PLAN mode
- Appended by ACT mode
- Appended by EVAL mode
- Always at a fixed, predictable path
- Safe to read at any point

What Goes in Context

PLAN mode writes:

  • Task description
  • Key design decisions and their rationale
  • Architecture choices
  • Dependencies and constraints
  • Recommended ACT agent

ACT mode writes:

  • Progress milestones completed
  • Files created/modified
  • Implementation decisions made
  • Issues encountered and resolved
  • Next steps

EVAL mode writes:

  • Quality findings (with severity)
  • Security issues found
  • Performance observations
  • Recommendations for next iteration

Context Document Format

# Context: [Task Title]

## PLAN — [timestamp]
**Task:** [Original task description]
**Primary Agent:** solution-architect
**Recommended ACT Agent:** agent-architect

### Decisions
- Decision 1: [What was decided and why]
- Decision 2: [What was decided and why]

### Notes
- Implementation note 1
- Constraint or dependency to remember

---

## ACT — [timestamp]
**Primary Agent:** agent-architect

### Progress
- [x] Created RulesService with search capability
- [x] Added Tests: 12 passing
- [ ] SSE transport implementation pending

### Notes
- Used glob for file discovery (faster than readdir recursion)
- NestJS module structure: McpModule → RulesModule

---

## EVAL — [timestamp]

### Findings
- [HIGH] Missing rate limiting on /sse endpoint
- [MEDIUM] Test coverage at 72%, below 80% target

### Recommendations
- Add rate limiting middleware
- Add tests for error cases in RulesService

Read the full file on GitHub · 246 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 · 246 lines · 38 tokens per session scan A b0699d2d728a

Subscribe to this mod's changes

context-management is a skill published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,410 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 2026-08-30.

Related

Other skills, from other repositories

om-integration-builder

Build integration provider packages for the Open Mercato Integration Marketplace (payment, shipping, data-sync, webhook). Scaffolds the npm package, adapter, credentials, widget injection, webhook processing, health checks, i18n, tests. Triggers on "build integration", "add provider", "integrate with…

open-mercato/open-mercato · 73 tokens

om-ds-guardian

Design System Guardian for Open Mercato. Use for frontend UI work, design-system compliance reviews, semantic token migration, hardcoded color or typography cleanup, DS-compliant page scaffolding, and common DS violations such as arbitrary text sizes, raw color classes, or missing shared states. Prefer this skill…

open-mercato/open-mercato · 76 tokens

om-integration-tests

Run and create QA integration tests (Playwright TypeScript), including executing the full suite, converting optional markdown scenarios, and generating new tests from specs or feature descriptions. Defers all environment boot/reuse to the om-prepare-test-env skill and attaches to the shared descriptor it writes. Use…

open-mercato/open-mercato · 99 tokens

om-auto-qa-scenarios

Generate a human QA report for a window of merged PRs (date floor, PR-number floor, or default last 7 days) and ship it as a docs-only PR against develop. Groups work into P0/P1/P2 testing routes with click paths, verification points, and risk callouts. Writes markdown + HTML under .ai/analysis/. Hands off to…

open-mercato/open-mercato · 99 tokens

om-create-agents-md

Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, the Always/Ask First/Never/Validation Commands boundary structure, MUST-style rules…

open-mercato/open-mercato · 85 tokens

om-smart-test

Run only the tests affected by changed code. Use when the user says "run affected tests", "run smart tests", "test only what changed", "run tests for this PR", "run tests for my changes", "selective tests", or asks to run tests without running the full suite.

open-mercato/open-mercato · 64 tokens