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 skills add kambleakash0/agent-skills --skill context-packgit clone --depth 1 https://github.com/kambleakash0/agent-skillsWrote 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.
[](https://agentmods.dev/skills/kambleakash0/agent-skills/context-pack)<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/context-pack"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/context-pack/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.
<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/context-pack"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/context-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00713 |
| Opus 5.5 | $0.00010 | $0.00285 |
| Sonnet 5.5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
context-pack 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Pack
Summarise the current conversation into a concise handoff document that a fresh agent can read to continue the work without losing context.
When to Use
Use this skill when:
- The user asks you to create a context pack or handoff document.
- The user wants to continue in a new agent session and needs context carried forward cleanly.
- A task is being handed to a different agent or a different person.
Do not use this skill to create project documentation or permanent records — that belongs in PRDs, ADRs, or spec files. This is a transitional document, not an artifact.
Behavior and Rules
- Save to the OS temp directory, not the current workspace. Use
/tmp,/var/tmp, or the equivalent for the user's OS. Name the file descriptively:context-pack-<dash-case-topic>-<YYYYMMDD>.md. - Don't duplicate existing artifacts. If a PRD, ADR, plan, spec, issue, commit, or diff already captures something, reference it by file path or URL — don't re-summarise it inline.
- Redact sensitive information. Strip any API keys, passwords, tokens, secrets, or personally identifiable information before writing.
- Tailor to the next session. If the user passed an argument describing what the next session will focus on, use it to weight what you include — surface the most relevant context for that goal and trim what won't matter.
- Be concise. The document should be scannable in under two minutes. Favour bullet points and short paragraphs over prose.
Document Structure
# Context Pack: {Topic or task}
## Context
{1–3 sentences: what this work is about and why it matters.}
## What was done this session
- {Key decision or action taken}
- {Another decision or action}
## Current state
{Where things stand right now — what is complete, what is in progress, what is blocked.}
## What to do next
- {The most important next step}
- {Other pending steps, in rough priority order}
## Key references
- {Path or URL to relevant PRD, spec, ADR, issue, commit, or diff}
- {Another reference}
## Suggested skills
- `/{skill-name}` — {one sentence on why it's relevant for the next session}
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.
- 1mo ago Changed 27abd553e886
- 2mo ago First seen · 71 lines · 25 tokens per session scan A 7f487b4e1395
context-pack is a skill published in the GitHub repository kambleakash0/agent-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 713 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.
context-pack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| context-packkambleakash0/agent-skills | Skill | 10 | 9d ago | MIT | A | 25 | Claude Code |
| context-engineeringaddyosmani/agent-skills | Skill | 114k | 5d ago | MIT | A | 43 | Claude Code |
| agent-memory-disciplinesickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 36 | Claude Code |
| agent-memorysickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 18 | Claude Code |
| ai-agents-architectsickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 31 | Claude Code |
| memory-managementThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 26 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |