agentmods.dev

capture-mcp-context

capture-mcp-context is a skill for Claude Code, Codex from Karthick-Ramachandran/persist-os. It costs 59 tokens per session (464 once invoked), scanned A, original, MIT.

A way to save useful information from connected tools such as Figma, Linear, Jira, or Sentry into the repository for later sessions. It records reusable facts and decisions rather than entire data exports.

In plain words
What is it for?
Use it after retrieving designs, tickets, error reports, or other project details from an external tool. It can record proposed context and accepted decisions in the project’s documentation.
Why use it?
External tool context can be lost between sessions or repeatedly looked up. Saving important design details, ticket requirements, and recurring errors makes that context available to future work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

not rated 8repo 2mo ago A scan 59 tokens original MIT

Good fit Use it after retrieving designs, tickets, error reports, or other project details from an external tool. It can record proposed context and accepted decisions in the project’s documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karthick-ramachandran/persist-os/capture-mcp-context
View source ↗ Karthick-Ramachandran/persist-os
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 Karthick-Ramachandran/persist-os --skill capture-mcp-context
Clone the repo
git clone --depth 1 https://github.com/Karthick-Ramachandran/persist-os

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 capture-mcp-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/capture-mcp-context/github.svg)](https://agentmods.dev/skills/karthick-ramachandran/persist-os/capture-mcp-context)
Your own site
<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/capture-mcp-context"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/capture-mcp-context/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 capture-mcp-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/capture-mcp-context"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/capture-mcp-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 464 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 $0.00059 $0.00464
Opus 5 $0.00030 $0.00232
Sonnet 5 $0.00012 $0.00093
Haiku 4.5 $0.00006 $0.00046

Measured 11d ago against content hash eea504393a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

capture-mcp-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 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.

.agents/skills/capture-mcp-context/SKILL.md · 60 lines

What it actually says

Skill: Capture MCP Context

Purpose

Persist the durable parts of MCP-derived external context so future sessions remember them instead of re-deriving them.

MCP provides context, not architectural truth.

Inputs

  • The MCP server or external tool in use (for example Figma, Linear, Jira, Sentry).
  • The external context retrieved (design tokens, tickets, errors, docs).
  • The current feature or task.

Required Reading

  • docs/ai/MCP_STRATEGY.md
  • Relevant docs/ai/mcp/<server>.md
  • Relevant feature and architecture docs.

Output Files

  • The Captured Context section of docs/ai/mcp/<server>.md.
  • An ADR via persist adr create when a captured decision is accepted.

Process

  1. Identify the MCP server and the durable facts worth remembering (design tokens, component mappings, ticket acceptance criteria, recurring error signatures).
  2. If docs/ai/mcp/<server>.md does not exist, create it with persist mcp add <server>.
  3. Record the durable context in the Captured Context section as proposed memory, with enough detail to reuse.
  4. Capture decisions, mappings, and constraints, not raw exports or full dumps.
  5. Treat MCP content as context, not truth; if it conflicts with accepted memory, stop and report.
  6. Promote any accepted decision into an ADR.

Stop Conditions

Stop and request human decision if:

  • MCP content conflicts with accepted repository memory.
  • Capturing the context would require storing secrets or sensitive data.
  • The MCP server is untrusted or its access is unclear.

Quality Bar

  • Captured context is durable and reusable, not a raw dump.
  • Each entry is concrete enough to guide future work.
  • MCP context is recorded as proposed, not accepted.
  • Accepted decisions are promoted to ADRs.
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 · 60 lines · 59 tokens per session scan A eea504393a1c

Subscribe to this mod's changes

capture-mcp-context is a skill published in the GitHub repository Karthick-Ramachandran/persist-os (8 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 464 once invoked, about $0.0003 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.

Claude CodeMemory and contextadragent-skillsai-agentsclideveloper-tools
Related

Other skills, from other repositories

learn

Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

automagik-dev/genie · 23 tokens

egregore

Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use.

egregore-labs/egregore · 64 tokens

init

Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.

rekal-dev/rekal-cli · 75 tokens

levelup-specify

Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.

tikalk/adlc-team-skills · 46 tokens

install

Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.

rekal-dev/rekal-cli · 66 tokens

change-publish

Promote accepted Change Decision Records (ChDRs) from drafts to project memory at .adlc/memory/chdr/, write OKF-style frontmatter, and regenerate the boot-facing .adlc/memory/chdr.md index that team-boot injects at session start. Use after /change-clarify has accepted ChDRs.

tikalk/adlc-team-skills · 73 tokens