mcp-digger: Skill for Claude Code

.claude/skills/load/SKILL.md

load is a skill for Claude Code from janeksm/mcp-digger. It costs 26 tokens per session (672 once invoked), scanned A, original, MIT.

A project-context loader that reads selected design, progress, decision, pattern and handoff files, then shows a summary. It waits for the user to choose the next task.

In plain words
What is it for?
It is for beginning a session, reviewing completed and remaining TODO items, and continuing from a saved handoff.
Why use it?
It gives the agent the project's current context without starting work or planning automatically.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is janeksm/mcp-digger's own configuration. It tells Claude Code how to work on mcp-digger itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-digger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to janeksm/mcp-digger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/janeksm/mcp-digger/main/.claude/skills/load/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/janeksm/mcp-digger

Made for: Claude Code.

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 load

README.md
[![agentmods](https://agentmods.dev/badge/skills/janeksm/mcp-digger/load/github.svg)](https://agentmods.dev/skills/janeksm/mcp-digger/load)
Your own site
<a href="https://agentmods.dev/skills/janeksm/mcp-digger/load"><img src="https://agentmods.dev/badge/skills/janeksm/mcp-digger/load/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 load

Your own site · 80×15
<a href="https://agentmods.dev/skills/janeksm/mcp-digger/load"><img src="https://agentmods.dev/badge/skills/janeksm/mcp-digger/load.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 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 $0.00026 $0.00672
Opus 5.5 $0.00010 $0.00269
Sonnet 5.5 $0.00005 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 2mo ago against content hash 42f29037f574, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

load 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 2mo 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.

.claude/skills/load/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load Project Context

Bootstrap a working session by loading project docs and CMCM knowledge files (decisions, patterns, handoff), then showing progress. Do NOT start planning automatically — wait for the user to choose what to work on.

Instructions

  1. Read project docs. Read all files in parallel (missing files are fine — skip silently):

    • DESIGN.md — current MCP server design
    • TODO.md — implementation progress
    • DECISIONS.md — CMCM: technical decision log (load into context, don't display)
    • PATTERNS.md — CMCM: reusable code patterns (load into context, don't display)
    • HANDOFF.md — CMCM: session continuity state (display if present)
  2. Session continuity. If HANDOFF.md exists and has content beyond the header, display it before the progress summary:

    --- Session Continuity ---
    Working on: <task from HANDOFF.md>
    State: <state>
    Next: <next step>
    ---
    

    If HANDOFF.md is missing or empty, skip this step silently.

  3. Show progress summary. From the TODO table, display:

    • The last completed step (highest step number with status done)
    • All remaining steps (any status other than done: —, in-progress, blocked)

    Format as a concise summary, e.g.:

    Last completed: Step 15 — dig_status MCP tool, lsRemote() connectivity check (a2ceae8)
    
    Remaining:
    | Step | Module | Status | Notes |
    |------|--------|--------|-------|
    | 10   | index.ts | —   | DRY version: read from package.json ... |
    
  4. Prompt for next action. After the progress summary, print exactly:

    Pick one:
      1. next — start the next unfinished step
      2. new  — describe a new task manually
    

    Stop and wait for the user's reply. On the next turn:

    • If the user picks next: invoke /dev <step-number> for the first remaining step from the TODO table.
    • If the user picks new: ask for the task description, then invoke /dev <description>.

Read the full file on GitHub · 70 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. 2mo ago First seen · 70 lines · 26 tokens per session scan A 42f29037f574

Subscribe to this mod's changes

load is a skill published in the GitHub repository janeksm/mcp-digger (0 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 672 once invoked, about $0.0001 per session on Opus 5.5. 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

git-workflow

Follow this team's Git conventions for branching, commit messages, and pull requests.

modelcontextprotocol/csharp-sdk · 19 tokens

orchardcore-scripting

Skill for using Orchard Core scripting and creating custom IGlobalMethodProvider implementations. Covers JavaScript evaluation with Jint, IScriptingManager and IScriptingEngine, disposing scripting scopes, built-in global methods, custom scripting providers that stay correct under lazy globals and engine reuse…

CrestApps/CrestApps.AgentSkills · 174 tokens

orchardcore-custom-indexing-elasticsearch

Skill for building a custom Elasticsearch index for arbitrary records in Orchard Core 4.0, following the CrestApps AI Memory pattern of CrestApps.OrchardCore 3.0. Covers a custom index profile type with AddElasticsearchIndexingSource, IndexProfileHandlerBase mappings with ElasticsearchIndexMetadata and dense vectors…

CrestApps/CrestApps.AgentSkills · 202 tokens

orchardcore-omnichannel-management

Skill for the CrestApps Omnichannel Management (CRM) module in Orchard Core. Covers CrestApps.OrchardCore.Omnichannel.Activities, ChannelEndpoints, Managements and Crm features; contacts with OmnichannelContactPart, IContactMethodsAccessor, IContactMethodsProvider and IContactMethodsWriter…

CrestApps/CrestApps.AgentSkills · 208 tokens

orchardcore-reports

Skill for building on the CrestApps Orchard Core Reports framework (CrestApps.OrchardCore.Reports, CrestApps.OrchardCore.Reports.OpenXml, CrestApps.OrchardCore.Reports.Subscriptions). Covers coded reports with static IReport descriptors and services.AddReport, report families with IReportRunner, ReportDescriptor and…

CrestApps/CrestApps.AgentSkills · 206 tokens

orchardcore-telephony

Skill for configuring and extending the provider-agnostic CrestApps Orchard Core Telephony module and its soft phone. Covers the Telephony, Soft Phone, Soft Phone Extension and Azure Blob Storage features, provider selection, capability-gated provider contracts, TelephonyHub events, dial destination safety…

CrestApps/CrestApps.AgentSkills · 198 tokens