load

A saved-project-context loader. It retrieves notes about the current project so you can resume work with its previous decisions, files, and next steps.

In plain words
What is it for?
Use it to catch up on saved context, review what you were working on, or show only sections such as decisions, files, or next steps.
Why use it?
It prevents you from losing track of where an earlier session stopped or repeating the same project discovery.

Skill for Claude CodeCodex

Part of the carry-forward plugin — 4 skills, 1 hook shipped together

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/gowtham012/claude-plugins/load
Any agent
npx skills add gowtham012/Claude-plugins --skill load
Clone the repo
git clone --depth 1 https://github.com/gowtham012/Claude-plugins

Made for: Claude Code, Codex.

Or install carry-forward, the plugin that ships this one along with the rest of its 4 skills, 1 hook.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00055 $0.00552
Opus 5 $0.00028 $0.00276
Sonnet 5 $0.00011 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 3d ago against content hash bd9285587bab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

carry-forward/skills/load/SKILL.md · 70 lines

What it actually says

Current time (for reference)

!date -u +"%Y-%m-%d %H:%M UTC" 2>/dev/null || echo "(unknown)"


Section filter (if provided)

$ARGUMENTS

If $ARGUMENTS is non-empty (e.g. "next steps", "decisions", "files"), show only that section of the context plus the Recent Activity log. Still call read_context to get the full data.


Instructions

Call mcp__carry-forward__read_context with cwd set to the current working directory.

If no context exists

Tell the user:

No saved context found for this project. Run /carry-forward:setup first, then use /carry-forward:save at the end of your next session.

If context exists — full load (no $ARGUMENTS filter)

Present it conversationally — not as raw markdown. Format your response as:


Picking up from your last session (saved DATE from frontmatter)

Current Task Restate in plain language. If the task is ambiguous or vague, say so.

Files in play List with brief notes. If git is available, cross-reference with git status mentally — note if files were removed or renamed since the save.

Key Decisions (still active) Include the WHY. If a decision seems outdated, flag it.

Next up Ordered list, most urgent first. If Next Steps are vague ("finish auth"), flag it and offer to clarify.

Open Questions (if any recorded)

Recent activity (last 10 log entries, most recent first)


Then close with:

Ready to continue. Want to start on [item 1 from Next Steps]?

Sparse or stale context

If the context is missing sections, has vague Next Steps, or the last_saved date is old (more than a few days), say so clearly:

"The saved context is missing [X]. Want me to help fill it in before we continue?"


Supporting files

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 70 lines · 55 tokens per session scan A bd9285587bab

Subscribe to this mod's changes

load is a skill published in the GitHub repository gowtham012/Claude-plugins (5 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 552 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.