What is push-updates?

A controlled publishing workflow that sends approved workspace updates to executive copies and related repositories using Git, a system for tracking file changes. It checks classifications, creates a release record, and reports the result.

Use it to review and publish workspace changes, update build and change records, push repositories, and refresh the operator's CRM summary.

It reduces the risk of publishing the wrong files or missing part of a coordinated update across repositories.

push-updates — Skill for Claude Code by mishahanin

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/mishahanin/heading-os

agentmods

npx agentmods add skills/mishahanin/heading-os/push-updates

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/push-updates.svg)](https://agentmods.dev/skills/mishahanin/heading-os/push-updates)

Your own site

<a href="https://agentmods.dev/skills/mishahanin/heading-os/push-updates"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/push-updates.svg" alt="Measured on agentmods" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,541 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00088	$0.02541
Opus 5	$0.00044	$0.01270
Sonnet 5	$0.00018	$0.00508
Haiku 4.5	$0.00009	$0.00254

Measured 3d ago against content hash 87353e53aec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

push-updates 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.

.claude/skills/push-updates/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Push Updates to All Executives

CEO-only skill. Single command to publish all workspace changes to all executives via the corporate repo.

Prerequisites

Read .workspace-identity.json - verify role is "admin". If not: "This skill is CEO-only." Stop.
Verify corporate repo exists at ../heading-os-corporate/. If not: "Corporate repo not found. Run initial setup first." Stop.

Variables

$ARGUMENTS - Optional summary of changes (used in BUILD.json and CHANGELOG)

Workflow

Read references/workflow.md before you run each phase below. It holds the preview format, the BUILD.json and CHANGELOG templates, and the report format. It also holds the v1.2 script mandate and the R16 staged rollout. The phases below carry every command line and every approval gate.

Working directory: run every command from the engine clone, which is the workspace root. No step changes it. A command that acts on another repository names that repository with git -C <path>, so no phase inherits a directory another phase moved to.

Phase 0: Pre-flight

Run python scripts/classification-health.py - report classification stats
Check for unclassified files: python scripts/classification-health.py --unclassified
- If any found: prompt CEO for classification of each file
- Add a rule to config/routing-map.yaml for any newly classified files

Check both trees for uncommitted changes:

git status --short
git -C ../.heading-os-data status --short

If uncommitted changes exist, show a summary and ask: "Commit these changes before pushing? (yes/no)"
Routing-regression gate (soft). Run:
```
python scripts/skill-trigger-test.py --changed --strict --threshold 0.85
```
Handle the exit code:
- 0 - proceed (no routing change, or all changed skills route correctly).
- 1 - below threshold, OR a changed skill the judge never returned a verdict for. Read which. MISS lines are routing regressions. NO VERDICT and Unmeasured lines mean the judge failed, not the router. Re-run in that case, rather than redrawing a trigger. Surface either to the CEO and ask for an explicit "proceed anyway" before continuing. Do NOT auto-block - this is a soft gate.
- 3 - no ANTHROPIC_API_KEY. Print a one-line warning that the routing check was skipped and proceed (never block publish on a missing key).
- 2 - setup error. Surface it and pause.

Read the full file on GitHub · 212 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 · 212 lines · 88 tokens per session scan A 87353e53aec2

Subscribe to this mod's changes

push-updates is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 2,541 once invoked, about $0.0004 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 2026-09-03.

Claude Code Git and workflow LLM Project management Releases Security ai-agent anthropic automation

release-manager

Use workflows, boards, hierarchy, and council together when coordinating a release or rollout.

aaronnat23/disp8ch · 0 tokens

github

Interact with GitHub using the gh CLI. Use for issues, PRs, CI runs, releases, and advanced API queries.

aretw0/agents-lab · 30 tokens

issue-draft-release-notes

Draft a customer-facing release note for a Jira ticket from its context and linked merge requests. Read-only unless the user opts in to publish. Use when the user says "draft release notes", "write a release note", "release note for [TICKET-KEY]", or invokes /issue-draft-release-notes.

risadams/ink-and-agency · 71 tokens

push-updates