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.
git clone --depth 1 https://github.com/Sagargupta16/claude-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/commands/sagargupta16/claude-skills/manage-context)<a href="https://agentmods.dev/commands/sagargupta16/claude-skills/manage-context"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-skills/manage-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/commands/sagargupta16/claude-skills/manage-context"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-skills/manage-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 | $0.00015 | $0.00167 |
| Opus 5 | $0.00008 | $0.00084 |
| Sonnet 5 | $0.00003 | $0.00033 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
manage-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 4d 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
Analyze the current session's context health:
- Estimate how much context has been used (based on conversation length and file reads)
- Check for signs of context rot (repeated mistakes, ignored rules, generic output)
- Recommend one of:
- Continue: Context is healthy, keep working
- Compact: Context is 40-60% full, compact with specific retention instructions
- Clear: Context is polluted with failed approaches, start fresh
- New session: Context is severely degraded or task is completely different
- If recommending compact, provide specific
/compactinstructions that retain the important context and drop the noise
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.
- 4d ago Changed 4815d8a17f4c
- 10d ago First seen · 16 lines · 15 tokens per session scan A b627ba141bc3
manage-context is a command published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 167 once invoked, about $0.0001 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 commands, from other repositories
commit
Create a git commit with intelligent message drafting (-f for fast, -v for verbose).
review-arch
Review app architecture: components, data flows, risks, and prioritized improvements.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
dream
Memory dream pass — judge undreamed days, promote durable signal to long-term, then sweep.
capture
Triage raw inbox notes into reviewed repository destinations without deleting their sources.
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.