reorient

A mid-task orientation aid for an coding agent that has lost track of its role, progress, or next step. It reloads the working rules and current task pointer without changing files.

In plain words
What is it for?
Use it after an interruption, when returning to a feature, or when you are unsure what to do next.
Why use it?
Long runs, interruptions, or context compaction can make an agent forget important instructions or repeat work. This helps it resume from the right place.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/swingerman/engineer/reorient
Any agent
npx skills add swingerman/engineer --skill reorient
Clone the repo
git clone --depth 1 https://github.com/swingerman/engineer

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.01515
Opus 5 $0.00040 $0.00758
Sonnet 5 $0.00016 $0.00303
Haiku 4.5 $0.00008 $0.00152

Measured 2d ago against content hash fd1993a18ed4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reorient 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 2d 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.

engineer/skills/reorient/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reorient

Restore the working contract mid-task. After a context compaction or a long run, an agent loses role identity, invents constraints that do not exist, skips required steps, and loses the task thread. reorient reloads the durable state that should have survived — the discipline contract first, the task pointer second.

Read-only and advisory. It changes nothing, produces no artifact, and emits no handoff — like next, the orientation block is the whole output; a handoff would only restate it. The third skill exempt from the agentic summary contract.

reorient is the mid-task, feature-scoped counterpart to next (project-scoped, session-start).

When to use

  • Right after a context compaction (a SessionStart hook can auto-invoke it).
  • Mid-task, when unsure of the role, the current checkpoint, or the next action.
  • Returning to a feature after an interruption.

Not for: session-start "what should I pick up across the project" (next); loading a feature not yet started (prime-context); validating artifacts (consistency-check).

Workflow

Step 1 — Resolve and locate

Resolve the methodology root + manifest via ${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py (see references/resolving.md). Locate the feature (slug arg or branch name). If no feature is in scope, say so and suggest next instead. Layout disambiguation: if the project has BOTH a features/NNN-*/ and a specs/NNN-*/ tree (a speckit migration in progress), say which one holds this feature; and if more than one acceptance-IR convention exists (features/NNN/.build/spec.json vs an acceptance-pipeline/ir/ per-GWT layout), name the one in force — so re-anchoring doesn't rediscover the split. (speckit-consolidate unifies it.)

Step 2 — Reload the discipline contract, then the task pointer

Read, read-only, in this order:

  1. Role + autonomyCHARTER.md + manifest: the autonomy level in force, and what the agent may and may not decide. Counters invented constraints.
  2. Current checkpoint + exit criteria — the Checkpoint Exit Contract (Foundation Design Section 8) for the checkpoint progress.md shows in progress: its goal, its exit criteria, and which are already met. Run ${CLAUDE_PLUGIN_ROOT}/scripts/dae_progress.py <feature-dir> and show its breadcrumb — the same pipeline-position line the checkpoint skills surface at Step 0.
  3. Non-negotiables — verification independence and charter-mandated mutation: steps that must not be skipped regardless of cost. The cost of a step is never a reason to skip it.
  4. Current task + next action — the progress.md CURRENT header.
  5. Feature contractfeature.md outcome + scope. Counters goal drift.

Read the full file on GitHub · 123 lines

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.

  1. 2d ago First seen · 123 lines · 80 tokens per session scan A fd1993a18ed4

Subscribe to this mod's changes

reorient is a skill published in the GitHub repository swingerman/engineer (146 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 1,515 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 2026-08-30.

Related

Other skills, from other repositories

writing-tests

Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.

hotovo/aider-desk · 48 tokens

release

Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.

lycorp-jp/sim-use · 61 tokens

work-summary

Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I…

jpicklyk/task-orchestrator · 110 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens

bmad-dev-story

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".

LarsCowe/bmalph · 40 tokens

bmad-editorial-review-structure

Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure.

LarsCowe/bmalph · 35 tokens