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/nicknisi/sessions/contextnpx skills add nicknisi/sessions --skill contextgit clone --depth 1 https://github.com/nicknisi/sessionsWrote 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/nicknisi/sessions/context)<a href="https://agentmods.dev/skills/nicknisi/sessions/context"><img src="https://agentmods.dev/badge/skills/nicknisi/sessions/context.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.00444 |
| Opus 5 | $0.00057 | $0.00222 |
| Sonnet 5 | $0.00023 | $0.00089 |
| Haiku 4.5 | $0.00011 | $0.00044 |
Grade A, and why
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 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
Synthesize a prose context primer from past sessions on this repo.
Steps
- Fetch the primer. Call the
get_context_primerMCP tool (passcwdif a path was given). - Synthesize, don't dump. From the JSON, write: prior decisions, what was tried/abandoned, and the current open thread.
- Anchor the open thread on the most-recent session's
closing—closing.useris the last thing you actually typed andclosing.assistantis the assistant's last substantive reply (outcomes like "PR is up: …" survive);branchis the branch you left off on. - Drill into a session worth expanding. If one primer session needs more than its opening/closing (an ambiguous open thread, a decision you need the details of), get its full arc from
get_session_digest: resolve the session'sfilePathviasearch_sessions(a distinctive phrase from itsintentplus the repo asproject), then digest that path. Expand a specific exchange withget_session_messages(offset: exchanges[].index)— don't page from 0. - Keep it tight — a short brief the user can act on, not a transcript.
Guidelines
- Prefer the most recent + most-edited files as the likely active surface.
- If the primer is empty, say so plainly; don't invent history.
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 · 28 lines · 114 tokens per session scan A a5f193bc3fd8
context is a skill published in the GitHub repository nicknisi/sessions (28 stars, last pushed 8d ago), licensed MIT. It adds 114 tokens to every session and 444 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
code-review
Review seekdb pull requests and diffs for high-signal correctness, resource-lifetime, concurrency, current-version state-consistency, credential-exposure, workflow-security, performance, and test-evidence defects. Use when reviewing changes to seekdb C++, Rust, build, CI, or test code; report only actionable Blocker…
ygrep
IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.
mikke
ノートフォルダ (Markdown KB) を mikke CLI で検索する。「○○について調べて」「過去のメモは?」「以前どう解決したか」等、過去の知見・記録を引き出す時に起動。最新仕様・時事・バージョン依存の質問では起動しない (Web が真)。.
dowse
Search the user's local files with dowse, a Windows full-text search index (Chinese + English, PDF/txt/md/code). Use this when the user asks you to find something on their disk — a note, a doc, a config, "that file about X" — instead of grepping the whole filesystem.
docingest-docs
Find, search, and read approved documentation snapshots through DocIngest.
session-recall
Recall past AI coding sessions as long-term memory. Use at the START of any non-trivial task, and whenever the user references earlier work ("like we did before", "the X we set up", "last time", "that bug fix"), asks who/when a file was changed, or you need context that predates this conversation. Runs the local…