Open Steps is a collection of coding-agent skills that explain development sessions, decisions, results, and next steps in plain language. It is intended for people who use agents to build software but do not want to rely on engineering jargon, and supports Claude Code, Codex, Cursor, and Gemini CLI. The catalogue entries provide the skills, hooks, plugin, and command that make up this workflow.
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 kharmanskyi/open-steps --skill os-big-picturegit clone --depth 1 https://github.com/kharmanskyi/open-stepsWrote 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/kharmanskyi/open-steps/os-big-picture)<a href="https://agentmods.dev/skills/kharmanskyi/open-steps/os-big-picture"><img src="https://agentmods.dev/badge/skills/kharmanskyi/open-steps/os-big-picture/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/kharmanskyi/open-steps/os-big-picture"><img src="https://agentmods.dev/badge/skills/kharmanskyi/open-steps/os-big-picture.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 | $0.00180 | $0.02049 |
| Opus 5.5 | $0.00072 | $0.00820 |
| Sonnet 5.5 | $0.00036 | $0.00410 |
| Haiku 4.5 | $0.00018 | $0.00205 |
Grade A, and why
os-big-picture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
os-big-picture
One file, BIG-PICTURE.md, where os-whats-next already looks for a backlog.
It answers "where are we now" - not a plan, nothing in it a promise. Write it
in the user's language; paths stay English.
When to use it. The user asks where the project stands, or there is no
BIG-PICTURE.md yet → the full pass: describe, census, signals, backlog. A
session report was just written → the fold-in: only the rows that session
touched. Both re-measure, because a session that moves no row is the one after
which the dates go quietly stale.
Step 1 - find the file, and never clobber it
BIG-PICTURE.md in the project root, and it may already be somebody's own
work. Everything this skill writes lives between <!-- open-steps:begin -->
and <!-- open-steps:end -->; no markers → append at the end; no file → create
it, and add it to this clone's ignore list, never to .gitignore:
f=BIG-PICTURE.md; e="$(git rev-parse --git-dir)/info/exclude"
git check-ignore -q "$f" || git ls-files --error-unmatch "$f" >/dev/null 2>&1 \
|| grep -qxF "$f" "$e" 2>/dev/null || printf '%s\n' "$f" >> "$e"
Each of the three is a reason to leave it alone. Say in one line that you did
it; git add -f BIG-PICTURE.md shares it instead. Never read Last worked on
or Signal back out of the file - only Stage and the queue carry forward.
Step 2 - the census, measured by the script
bash ${CLAUDE_SKILL_DIR}/scripts/census.sh .
Where your tool does not set ${CLAUDE_SKILL_DIR}, run it from the project
root as bash <this skill's folder>/scripts/census.sh .. If it cannot run at
all, say so and mark every measured column "not checked"; never estimate them.
An AGE line, then one measured PART row per part: path, last worked on,
commits in six months, whether anything outside reaches it, the signal.
Step 3 - reading what it printed
| Signal | What it means | What to do |
|---|---|---|
active |
Being worked on | Nothing |
stable |
Quiet, and something still reaches it | Leave it alone - finished and in use |
unused - N months |
Quiet, and nothing reaches it | The only real retire candidate |
What ships with it
3 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.
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.
- 23d ago Changed · -1 lines 81f265595cf9
- 27d ago Changed · -1 lines ed5b2defd246
- 29d ago Changed · +6 lines b9d7475ed4f2
- 1mo ago First seen · 167 lines · 180 tokens per session scan A ee471fd26f66
os-big-picture is a skill published in the GitHub repository kharmanskyi/open-steps (1,244 stars, last pushed 22d ago), licensed MIT. It adds 180 tokens to every session and 2,049 once invoked, about $0.0007 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 2026-09-12.
Other skills, from other repositories
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
autogap
High-value project analyst + impl strategist. Any project type (code, docs, research, strategy, workflow, creative, ops, non-tech, hybrid). Inspect deep, infer top-value objective from signals, find top 3 gaps, propose 3 macro-steps user picks (none/one/two/all). After pick, plan + implement autonomously. Triggers…
capacity-planner
Use when an ops leader (Director of CX, Head of Support, VP Ops, Head of BizOps, Head of IT ops, Head of Finance ops) is sizing ops capacity, building a headcount plan, modeling utilization risk, planning Q3 capacity or annual support capacity, or designing CS coverage — and needs Erlang-C queueing math, P90 demand…
business-operations-skills
Use when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring, procurement spend. Triggers on "BizOps review", "where's the bottleneck", "vendor health", "internal SOP", "all-hands deck", "spend categorization"…
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…