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.
npx agentmods add skills/gowtham012/claude-plugins/loadnpx skills add gowtham012/Claude-plugins --skill loadgit clone --depth 1 https://github.com/gowtham012/Claude-pluginsWhat 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.
| Model | Per session | Once 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 |
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.
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:setupfirst, then use/carry-forward:saveat 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
- examples/sample-context.md — example of a well-presented context summary
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.
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.
- 3d ago First seen · 70 lines · 55 tokens per session scan A bd9285587bab
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.
Other skills, from other repositories
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
bot2bot-post
Post a coordination message from this bot to the shared bot2bot channel — @-mentioning a specific peer via --to, auto-mentioning only in single-peer fleets, never guessing.