Agent skill

Refresh Context

by real-simple-labs in real-simple-labs/parker-brain

Keep the brand brain from going stale. An agent skill from real-simple-labs/parker-brain.

Custom licenceAuto-check passed

Install Refresh Context

skills CLI
$ npx skills add real-simple-labs/parker-brain --skill refresh-context -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install real-simple-labs/parker-brain refresh-context --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/real-simple-labs/parker-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/refresh-context .claude/skills/refresh-context && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
refresh-context
GitHub stars
100
Token cost
~2.8k tokens
SKILL.md length
1,524 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Custom licence

At a glance

Keep the brand brain from going stale. An agent skill from real-simple-labs/parker-brain.

  • Works in 9 steps: Read the schedule. Open… → Compare to today. Read today from… → Walk the phase spine for dependency… → …
  • SKILL.md covers When it runs, The freshness mechanism, Process and Hard rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Refresh Context is an agent skill from real-simple-labs/parker-brain. Keep the brand brain from going stale. Reads running-notes/refresh-schedule.md and each standing doc's refreshby frontmatter, surfaces what is overdue or due soon, walks the Phase 1→2→3 dependency spine to catch docs made stale by upstream changes even when their own date is fine, and re-runs the generating prompt for each — carrying the prior version forward and re-stamping the dates. Use weekly as a scheduled routine, or whenever asked to refresh, re-run, or check the freshness of the brand brain or any context…

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

Example prompts

  • “/refresh-context”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Read the schedule. Open running-notes/refresh-schedule.md. If it is missing (a fresh brain may not have one yet), build it: walk every…
  2. Compare to today. Read today from get_current_time. Mark each doc overdue, due soon (within ~2 weeks), or fresh. Then scan for fired…
  3. Walk the phase spine for dependency staleness. After the date pass, check the Phase 1→2→3 chain: for each downstream doc (the four Phase-2…
  4. Surface before acting. List what is overdue / due-soon / stale-by-dependency with one line each — "your performance read is from March and…
  5. Re-run each due doc, and note whether the read changed. A refresh is a re-run of the generating prompt, not a patch. The prompt lives in…
  6. Update the schedule line for every doc re-run, so refresh-schedule.md stays a true aggregate. When a re-run materially changed the read…
  7. Refresh the folder indexes. If a refresh added, removed, or materially changed a competitor profile or an audit, regenerate that folder's…
  8. Close the loop. If a refresh surfaced something new — a shift the old read missed — capture it as an open loop in open-loops/ for the next…
  9. Log the run. Prepend one entry to running-notes/routine-log.md (create it from parker-system/templates/routine-log-template.md if it does…

What it can do on your machine

Read from SKILL.md and the folder at commit 62c4f72. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Refresh Context loads about 2.8k tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 1,524 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~135
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,524 words (~2,805 tokens).

“A context doc is a photograph of a moving thing. The ad account moves weekly, reviews pile up, a competitor enters, the brand relaunches. Every standing doc carries a refresh_by date; this routine watches those dates so a stale doc…”

— opening of SKILL.md by real-simple-labs, Custom licence
name
refresh-context
argument-hint
[optional: a doc name or cadence tier to refresh; default = everything overdue]

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/refresh-context of real-simple-labs/parker-brain.

Open the folder on GitHubat commit 62c4f72

Compare with similar skills

Refresh Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Refresh Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Refresh Context this skillreal-simple-labs/parker-brain100—~2.8kAutomated safety check: PassCustom licence
Index Refreshpaperclipai/paperclip99k—~994Automated safety check: PassMIT
Meta Refreshthedaviddias/Front-End-Checklist74k—~434Automated safety check: PassMIT
Brainjeremylongshore/tons-of-skills-marketplace2.8k—~1.9kAutomated safety check: PassApache-2.0
Go In Depthsickn33/agentic-awesome-skills47k1 repos~530Automated safety check: PassMIT
Collectors Go Framework V2netdata/netdata81k—~5.7kAutomated safety check: PassGPL-3.0

Similar skills

  • Index Refresh

    paperclipai/paperclip

    A skill your agent uses when an LLM Wiki operation issue requests an index refresh.

    99k GitHub stars~994 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Meta Refresh

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid meta refresh redirects.

    74k GitHub stars~434 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Brain

    jeremylongshore/tons-of-skills-marketplace

    Answers questions about your own systems, notes, decisions, runbooks, and conventions from your governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall.

    2.8k GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Go In Depth

    sickn33/agentic-awesome-skills

    Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

    47k GitHub starsUsed in 1 repo~530 tokens
    Research & ScienceAuto-check passed
  • Implement, migrate or review Go go.d framework V2 collectors, CollectorV2 lifecycle, metrix metric stores, charts.yaml authoring (defaults, families, ordering, statesets, labels)…

    81k GitHub stars~5.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Brain Taxonomist

    garrytan/gbrain

    Filing gate for ALL brain writes. An agent skill from garrytan/gbrain.

    31k GitHub stars~2.3k tokensUpdated today
    DevOps & CloudAuto-check passed

More from real-simple-labs/parker-brain

All 20 skills in this repo
  • Open Loops Advance

    real-simple-labs/parker-brain

    Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the…

    100 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Open Loops Validate

    real-simple-labs/parker-brain

    Run a hypothesis's test plan, gather the evidence, and honestly resolve the loop into one of the four validation states — validated, invalidated, inconclusive, or insufficient evidence.

    100 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Propagate Craft

    real-simple-labs/parker-brain

    Push-based re-ship of the factory methodology bundle into brand brains that carry the method as copied files — the legacy vendored-parker-system layout and decoupled brains that asked for a refresh.

    100 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Update Parker Skill

    real-simple-labs/parker-brain

    Make a correct update to Parker's prompts, system docs, rubrics, knowledge docs, training corpus, or brand outputs — and propagate the change everywhere it needs to land.

    100 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Ad Account Analysis

    real-simple-labs/parker-brain

    Analyze Meta ad account data — read what's spending, what's converting, what's fatiguing, and where the audience is being reached.

    100 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Dream

    real-simple-labs/parker-brain

    Run the dreaming system on demand for a brand and the person using it.

    100 GitHub stars~3k tokensUpdated today
    Auto-check passed

Questions about Refresh Context

What does Refresh Context do?

Keep the brand brain from going stale. An agent skill from real-simple-labs/parker-brain. Refresh Context is an agent skill from real-simple-labs/parker-brain. Keep the brand brain from going stale.

How do I install Refresh Context in Claude Code?

Run `npx skills add real-simple-labs/parker-brain --skill refresh-context -a claude-code`. Or copy the skill folder (.claude/skills/refresh-context in real-simple-labs/parker-brain) into .claude/skills/refresh-context in your project. Claude Code loads it when a task matches its description.

How do I install Refresh Context in Codex?

Run `npx skills add real-simple-labs/parker-brain --skill refresh-context -a codex`. Or copy the skill folder (.claude/skills/refresh-context in real-simple-labs/parker-brain) into .agents/skills/refresh-context in your project. Codex loads it when a task matches its description.

Can I use Refresh Context in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add real-simple-labs/parker-brain --skill refresh-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refresh-context, .gemini/skills/refresh-context, .github/skills/refresh-context and .opencode/skills/refresh-context in your project.

What does Refresh Context need to run?

SKILL.md names no scripts, command-line tools or credentials: Refresh Context is instructions for the agent only.

Does Refresh Context access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Refresh Context safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Refresh Context use?

Refresh Context has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Refresh Context use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Refresh Context?

Skills that share tags, products or a category with Refresh Context: Index Refresh (paperclipai/paperclip, 99k stars), Meta Refresh (thedaviddias/Front-End-Checklist, 74k stars), Brain (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Go In Depth (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refresh Context?

real-simple-labs (a GitHub organization) maintains it in real-simple-labs/parker-brain, which has 100 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 7, 2026.

Source: real-simple-labs/parker-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.