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 restarter/lets-workflow --skill orientgit clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/restarter/lets-workflow/orient)<a href="https://agentmods.dev/skills/restarter/lets-workflow/orient"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/orient/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/restarter/lets-workflow/orient"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01584 |
| Opus 5.5 | $0.00017 | $0.00634 |
| Sonnet 5.5 | $0.00008 | $0.00317 |
| Haiku 4.5 | $0.00004 | $0.00158 |
Grade A, and why
orient 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient Snapshot
Render the shared "where am I / what's in flight / what's next" snapshot. Consumed by /lets:status (snapshot, then stop), /lets:start (snapshot + pick/claim), and /lets:backlog --fast (snapshot + dialog). Single source of truth so the three never drift.
This skill ONLY gathers + renders the snapshot block. It does NOT select, claim, mutate, or advise. The caller appends its own follow-through.
Built on git + detect-task + neutral tracker verbs, so it degrades cleanly on any tracker (beads | none | a custom adapter).
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own - the tool invocation is part of the contract.
Step 1: Active task
Invoke Skill(skill: "lets:detect-task") -> an id or None. (A skill may invoke another skill; this is a normal nested Skill-tool call in the same orchestrator context.)
Inline fallback (only if the nested Skill call is unavailable - rare: skill-invokes-skill is sound, this is belt-and-suspenders): do NOT re-derive the id with a partial copy of detect-task's precedence ladder (it would rot when the branch format changes and would drop detect-task's merge-branch liveness check + its search-and-confirm fallback). Instead skip the active-task line and note it degraded - the In flight section (Step 3) still surfaces any in_progress task. detect-task stays the single source of branch-format truth.
When Step 1 yields an id, get its title with the tracker's show:
Tracker protocol: Skill(skill: "lets:protocol-tracker") before this and any later lets-tracker block here, unless its text is in your current context.
show task=<id> # returns {id, title, status, url}
Step 2: Git state
git branch --show-current
git status --short # empty = clean; else count the lines
Detect context (one compact line, only if applicable): worktree (git-dir contains worktrees/), trunk-mode (HEAD == {LETS_MERGE_BRANCH} AND an active task), or main-mode (HEAD == {LETS_MERGE_BRANCH}, no task).
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 Changed · -1 lines d323197137c5
- 19d ago Changed · +2 lines 2dc26ec1b893
- 1mo ago Changed · +21 lines d5a81e2cbd75
- 1mo ago First seen · 102 lines · 42 tokens per session scan A 4341d19ec255
orient is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,584 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…
dekko-review-context
Give a code-review or PR-description flow a structural head start before reading a diff line by line. Trigger when the user asks for a PR description, a pre-merge summary, or invokes a code-review flow (/code-review, /review, or an equivalent) against a diff in a repo with a .dekko/ directory.
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
fix
Read this repo's open issues, triage them, and open one pull request per issue that can be fixed without a judgement call. Issues that need a decision, or that look stale or superseded, are reported with a recommendation rather than guessed at.
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
review-health
Audit any repository's structural health and prompt surface, and file the findings as proposed epics and one-PR issues.