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 cnfeat/top-pm-skills --skill context-modegit clone --depth 1 https://github.com/cnfeat/top-pm-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/cnfeat/top-pm-skills/context-mode)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/context-mode"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/context-mode/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/cnfeat/top-pm-skills/context-mode"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/context-mode.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 | $0.00085 | $0.01835 |
| Opus 5.5 | $0.00034 | $0.00734 |
| Sonnet 5.5 | $0.00017 | $0.00367 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
context-mode 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Mode Skill
Fix the two session killers that end most Claude Code sessions in under 30 minutes: context bloat from raw command output, and memory loss after a reset.
Context Mode runs three systems simultaneously to keep sessions alive:
- Output Filtering — strips verbose command output before it enters context
- Session Log — writes a running log of everything that happened
- Auto-Resume — reads the log on reset and picks up exactly where you left off
Credit: Inspired by a skill from Nate Herk's YouTube channel — adapted and extended for this library.
Required Inputs
No inputs required. Context Mode activates on command.
Optional: user can specify a custom log file path if they don't want session.log in the project root.
How Context Mode Works
Part 1 — Output Filtering
The problem: every time Claude Code runs a command, the full raw output enters the context window. A single npm install can dump hundreds of lines. A test suite run? Thousands. Within 30 minutes, the context is full of noise and Claude resets.
The fix: before any command output enters context, filter it to the useful summary only.
What gets kept:
- Last 10 lines of stdout
- Every line containing
error,warn,fail,exception,traceback, orfatal(case-insensitive) - The exit code
- A one-line summary of what the command did and whether it succeeded
What gets discarded:
- Middle section of long stdout (replaced with
[... N lines of output truncated ...]) - Progress bars, download indicators, verbose install logs
- Repeated identical lines (deduplicated)
Filtering summary format:
COMMAND: [command run]
STATUS: [exit code — success / failed]
SUMMARY: [one sentence: what happened]
ERRORS: [any error/warn lines — or "none"]
TAIL: [last 10 lines of stdout]
Part 2 — Session Log
Claude maintains a running log file at [project root]/session.log. This file is written after every significant action and is the source of truth for resuming after a reset.
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 First seen · 249 lines · 85 tokens per session scan A 27a6970c3508
context-mode is a skill published in the GitHub repository cnfeat/top-pm-skills (55 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 1,835 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…