Agent skill

Context Propagation

by dxos in dxos/dxos

Rules for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces connected trace hierarchies.

Custom licenceAuto-check passed

Install Context Propagation

skills CLI
$ npx skills add dxos/dxos --skill context-propagation -a claude-code

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

GitHub CLI
$ gh skill install dxos/dxos context-propagation --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/dxos/dxos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/context-propagation .claude/skills/context-propagation && 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
context-propagation
GitHub stars
526
Token cost
~4.3k tokens
SKILL.md length
1,413 words
Files
2
Skills in repo
41
Repo updated
First seen
Licence
Custom licence

At a glance

Rules for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces connected trace hierarchies.

  • Works in 6 steps: Direct calls: forward the caller's ctx → Event subscriptions and callbacks: use… → Detached async work: use class lifecycle… → …
  • Adding context propagation
  • SKILL.md covers Why This Matters, Which Methods Need ctx, Rules and How Context Flows, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Context Propagation is an agent skill from dxos/dxos. Rules for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces connected trace hierarchies. Use when adding context propagation, reviewing ctx usage, fixing broken traces, or when code uses @trace.span(), Context, or this.ctx.

Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `AUDIT.md`).

The repository describes itself as: TypeScript implementation of the DXOS protocols, SDK, toolchain and Composer.

When your agent uses it

  • Adding context propagation
  • Reviewing ctx usage
  • Fixing broken traces
  • Code uses @trace.span()

Example prompts

  • “Use the context-propagation skill to rule for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces…”
  • “/context-propagation”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Direct calls: forward the caller's ctx
  2. Event subscriptions and callbacks: use lifecycle ctx
  3. Detached async work: use class lifecycle ctx
  4. Parallel fan-out: share the parent ctx
  5. Reassign ctx to the return value of trace.spanStart()
  6. Complete call chain: every method between entry point and @trace.span must forward ctx

What it can do on your machine

Read from SKILL.md and the folder at commit 085dcb1. 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 (its code samples are typescript).

    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

Context Propagation loads about 4.3k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 1,413 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k

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 1,413 words (~4,265 tokens).

“Every internal method takes ctx: Context as its first parameter (Go-style). The @trace.span() decorator detects ctx as args[0], uses it as the parent span, and replaces it with a child context before calling the method body. This enables hierarchical OTEL…”

— opening of SKILL.md by dxos, Custom licence
name
context-propagation

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .agents/skills/context-propagation of dxos/dxos.

  • SKILL.md
  • AUDIT.md

Open the folder on GitHubat commit 085dcb1

Compare with similar skills

Context Propagation 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.

Context Propagation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Propagation this skilldxos/dxos526—~4.3kAutomated safety check: PassCustom licence
Internal Commsalirezarezvani/claude-skills28k—~3.4kAutomated safety check: PassMIT
Parametersthedaviddias/Front-End-Checklist74k—~638Automated safety check: PassMIT
Internal Communicationsickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT
Internal Communications Writeranthropics/skills180k38 repos~378Automated safety check: PassApache-2.0
Internal Comms Anthropicsickn33/agentic-awesome-skills47k1 repos~702Automated safety check: PassApache-2.0

Similar skills

  • Internal Comms

    alirezarezvani/claude-skills

    A skill your agent uses when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement…

    28k GitHub stars~3.4k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Parameters

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing URL structure or configuring search engine handling of filtered, sorted, or tracked URLs.

    74k GitHub stars~638 tokensUpdated 3 days ago
    Sales & SupportAuto-check passed
  • Internal Communication

    sickn33/agentic-awesome-skills

    Internal communication log: title, type, date, department, host and attendees, agenda, action items, follow-up date, meeting link and delivery status.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Writing & ContentAuto-check passed
  • Official

    A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill…

    180k GitHub starsUsed in 38 repos~378 tokens
    Writing & ContentAuto-check passed
  • Internal Comms Anthropic

    sickn33/agentic-awesome-skills

    Compatibility alias for internal-comms: draft status updates, newsletters and FAQs from approved sources.

    47k GitHub starsUsed in 1 repo~702 tokens
    Writing & ContentAuto-check passed
  • Nofollow Internal

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing internal link structure or reviewing link attributes.

    74k GitHub stars~579 tokensUpdated 3 days ago
    Auto-check passed

More from dxos/dxos

All 41 skills in this repo
  • Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…

    526 GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Forensically inspect and repair Composer browser profiles — offline (Chrome OPFS / SQLite extract) or live via /recovery.html debug port.

    526 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Migrate Oxfmt

    dxos/dxos

    Guide for migrating a project from Prettier or Biome to Oxfmt.

    526 GitHub starsUsed in 3 repos~2.2k tokens
    Auto-check passed
  • Moon

    dxos/dxos

    This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon…

    526 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Reference for SubductionPolicy (the four hooks authorizeConnect, authorizeFetch, authorizePut, filterAuthorizedFetch passed via Subduction.hydrate(..., policy) or new Repo({ subductionPolicy })).

    526 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Autocue

    dxos/dxos

    Record a demo of the running app that the agent drives itself — a .mdl QA test or an ad-hoc walkthrough — as a captioned .webm (or a screenshot), trimmed of dead air and ready to attach.

    526 GitHub stars~13k tokensUpdated today
    Auto-check: notes

Questions about Context Propagation

What does Context Propagation do?

Rules for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces connected trace hierarchies. Context Propagation is an agent skill from dxos/dxos.span() produces connected trace hierarchies.

When should I use Context Propagation?

Context Propagation fits situations like: adding context propagation; reviewing ctx usage; fixing broken traces; code uses @trace.span().

How do I install Context Propagation in Claude Code?

Run `npx skills add dxos/dxos --skill context-propagation -a claude-code`. Or copy the skill folder (.agents/skills/context-propagation in dxos/dxos) into .claude/skills/context-propagation in your project. Claude Code loads it when a task matches its description.

How do I install Context Propagation in Codex?

Run `npx skills add dxos/dxos --skill context-propagation -a codex`. Or copy the skill folder (.agents/skills/context-propagation in dxos/dxos) into .agents/skills/context-propagation in your project. Codex loads it when a task matches its description.

Can I use Context Propagation 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 dxos/dxos --skill context-propagation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-propagation, .gemini/skills/context-propagation, .github/skills/context-propagation and .opencode/skills/context-propagation in your project.

What does Context Propagation need to run?

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

Does Context Propagation 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 Context Propagation 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 Context Propagation use?

Context Propagation 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 Context Propagation use?

About 4.3k tokens (SKILL.md is roughly 17k 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 Context Propagation?

Skills that share tags, products or a category with Context Propagation: Internal Comms (alirezarezvani/claude-skills, 28k stars), Parameters (thedaviddias/Front-End-Checklist, 74k stars), Internal Communication (sickn33/agentic-awesome-skills, 47k stars) and Internal Communications Writer (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Propagation?

dxos (a GitHub organization) maintains it in dxos/dxos, which has 526 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 10, 2026.

Source: dxos/dxos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.