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 adeotek/claude-code --skill save-contextgit clone --depth 1 https://github.com/adeotek/claude-codeWrote 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/adeotek/claude-code/save-context)<a href="https://agentmods.dev/skills/adeotek/claude-code/save-context"><img src="https://agentmods.dev/badge/skills/adeotek/claude-code/save-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.
<a href="https://agentmods.dev/skills/adeotek/claude-code/save-context"><img src="https://agentmods.dev/badge/skills/adeotek/claude-code/save-context.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 | $0.00108 | $0.00825 |
| Opus 5.5 | $0.00043 | $0.00330 |
| Sonnet 5.5 | $0.00022 | $0.00165 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
save-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 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Context
Save a compact summary of the current session to .memory/<name>.md in the current working directory, using fixed sections for consistent, scannable output.
Steps
-
Extract the filename from the user's prompt. Convert to kebab-case (e.g., "auth work" →
auth-work, "JWT feature" →jwt-feature). The display name in the heading preserves the user's original phrasing. -
Check for an existing file. If
.memory/<name>.mdalready exists, ask the user whether to overwrite it before proceeding. Do not overwrite silently. -
Gather git state by running these commands:
git branch --show-current 2>/dev/null git log --oneline -3 2>/dev/nullIf either fails (not a git repo), omit the git line from the output entirely.
-
Create the
.memory/directory in the current working directory if it doesn't exist:mkdir -p .memory -
Write
.memory/<name>.mdusing the template below, populated from the current conversation. -
Confirm the saved file path to the user (e.g., "Saved to
.memory/auth-work.md").
Template
# Context: <user's original name>
**Saved**: YYYY-MM-DD | **Directory**: <absolute cwd>
**Branch**: <branch> | **Recent commits**: <hash> <msg>, <hash> <msg>, <hash> <msg>
## Goal
<What was being worked on and why — one focused paragraph>
## Current State
<What's done, what's in progress, what's blocked — be specific about status>
## Key Files
- `<path/to/file>` — <what changed or why it matters>
## Decisions Made
- **<decision>**: <rationale — especially non-obvious choices>
## Next Steps
- [ ] <concrete action item>
## Notes
<Caveats, gotchas, blockers, or background that would be easy to forget>
Omit the git line entirely if not in a git repo. Omit any section that has nothing meaningful to say — never write "N/A" or leave a section empty.
Content Guidelines
Goal: One paragraph describing the task and motivation. Focus on why, not just what.
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.
- 2mo ago First seen · 75 lines · 108 tokens per session scan A 72a3ba36a727
save-context is a skill published in the GitHub repository adeotek/claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 108 tokens to every session and 825 once invoked, about $0.0004 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.
save-context compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| save-contextadeotek/claude-code | Skill | 2 | 6mo ago | MIT | A | 108 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 0 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |
| memoryopensquilla/opensquilla | Skill | 7.1k | 7d ago | Apache-2.0 | A | 44 | Claude Code, Codex |