⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
coding-posture
Use before non-trivial coding work to pick a task-appropriate working mode — debug, fix, review, test-first, refactor, optimize, migrate, upgrade, integrate, spike, or unstuck — then follow its checklist. Modes are procedures, not personas. Not needed for trivial one-line edits or non-coding tasks.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
Coding Posture
Task-aware working modes for coding agents. One SKILL.md file: before non-trivial work, the agent picks a mode — debug, fix, review, test-first, refactor, optimize, migrate, upgrade, integrate, spike, unstuck — and follows its checklist.
It exists to stop agents from behaving like optimistic elevators with write access: thrashing on a stuck bug, faking green tests, skipping reproduction, running destructive commands, migrating without a rollback.
Works with Hermes · Claude Code · Codex · Cursor · Pi — any SKILL.md-compatible agent.
How the agent uses it
flowchart TD
Task["Non-trivial coding task"] --> Pick{"Pick a mode that fits<br/>(debug, fix, review, migrate, …)"}
Pick -->|no match| Normal["Proceed normally"]
Pick -->|match| Check["Follow the mode's checklist"]
Check --> Loop["gather context → localize → smallest change<br/>→ run the real check → read output"]
Loop --> V{"Verified by a real run?"}
V -->|no| Loop
V -->|yes| Done(["Done"])
Guard["Always-on invariants:<br/>no fake green · no destructive commands · don't game tests"] -.->|guards every step| Check
Guard -.-> Loop
Modes
| Mode | Use when | Core discipline |
|---|---|---|
debug | failing test, bug, regression | reproduce first, one hypothesis at a time |
fix | small known urgent change | smallest diff, no opportunistic cleanup |
review | security/auth/payments, reviewing a diff | no approval without file/line evidence |
test-first | behavior change, tests practical | see RED before implementing, never fake green |
refactor | cleanup, simplify, rename | preserve behavior, trace call sites before deleting |
optimize | performance work, hot path | measure first, baseline before/after |
migrate | schema/data/infra change | rollback path before touching state |
upgrade | dependency or version bump | read breaking changes, no blind search-replace |
integrate | calling an external API/service | read the contract, handle the error paths |
spike | prototype, PoC, unknown library | isolate, end with a verdict |
unstuck | repeated failures, thrashing | stop editing, summarize evidence, narrow hypotheses |
Always — in every mode:
- Verify by running the real check (test, build, repro); never by re-reading.
- Never report a result you didn't run; never weaken, delete, or game a test to go green.
- No destructive commands (
force push,reset --hard,drop,rm -rf) without explicit scope.
Install
Install as a plugin (one command, updates in place) or drop the skill in directly. It's a standard SKILL.md skill, so it works unmodified across compatible agents.
Claude Code — plugin
/plugin marketplace add alexei-led/coding-posture
/plugin install coding-posture@coding-posture
Update later with /plugin marketplace update coding-posture then /reload-plugins, or enable auto-update from the /plugin menu to refresh on startup.
Codex CLI — plugin
git clone [email protected]:alexei-led/coding-posture.git
codex # then: /plugins → add the local marketplace in ./coding-posture → install coding-posture
Or point Codex straight at the skill in ~/.codex/config.json:
{ "skills": ["/abs/path/to/coding-posture/skills/coding-posture"] }
Update later with git pull.
Other agents
| Agent | Install |
|---|---|
| Hermes | Drop skills/coding-posture/ into ~/.hermes/skills/ (auto-discovered). URL/hub install: see the Hermes skills docs. |
| Pi | pi install git:github.com/alexei-led/coding-posture |
Cursor / any SKILL.md agent | Copy skills/coding-posture/ into the agent's skills dir. |
The agent activates the skill from its description when a coding task starts.
How it works — theory and evidence
A skill is just text placed in the model's context. A worked procedure acts as an in-context demonstration: the model conditions its next tokens on the shown trajectory, not just the final answer — the same basis as chain-of-thought. No complete mechanistic theory of frontier-model reasoning exists yet, so treat this as a grounded substrate, not a proof.
Each design claim, and how strong the evidence actually is:
| Claim | Evidence strength | Sources |
|---|---|---|
| A checklist shifts behavior via in-context conditioning | Grounded substrate, not a full theory | CoT (Wei 2022), induction heads (Olsson 2022), iteration heads (NeurIPS 2024), ICL/CoT (ICML 2024) |
| Procedures beat personas | Supported guideline, not a law | personas don't help (Zheng 2024), self-consistency (2022) |
| The model self-selects the mode | Holds for strong models, not universal | Route-to-Reason (2025) |
// HOW IT'S BUILT
KEY FILES