Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Pin

ASecurity

Anchor this session to one goal — the message, target, or outcome it keeps working toward across loops, wakeups, compactions, and hand-offs — and check progress against it.

85 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobash

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add indigoai-us/hq-core --skill pin --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pin?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pin
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/indigoai-us-pin/badge)](https://www.skillsdirectory.com/skills/indigoai-us-pin)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: pin
description: Anchor this session to one goal — the message, target, or outcome it keeps working toward across loops, wakeups, compactions, and hand-offs — and check progress against it.
allowed-tools: Bash(bash core/scripts/hq-pin.sh:*), Bash(core/scripts/hq-pin.sh:*), Read
---

# /pin — the goal this session is anchored to

A pin is the one thing the session is for. Once set, every status tick, wakeup,
and post-compaction resume starts by re-reading it, and the session does not
stop until the pin's done criteria are met or the owner clears it.

Script: `core/scripts/hq-pin.sh` (set · show · check · note · done · clear).

## Usage

```
/pin <goal>                     set the pin (goal text; add done criteria in the same call)
/pin                            show the current pin
/pin done <criterion text>      mark one done-criterion met
/pin note <progress>            append a dated progress line
/pin clear                      remove the pin
```

## Set

```bash
bash core/scripts/hq-pin.sh set "Ship agents v3 for every company and retire the old runtime" \
  --done "every production agent runs the current runtime" \
  --done "old-runtime boxes are deprovisioned" \
  --done "live smoke passes and a standing monitor watches it" \
  --owner "the owner" --channel "project-launch"
```

Write the goal as an outcome, and write each done criterion so a reader can
check it without asking anyone. A pin with no done criteria is a slogan; add at
least one.

## Behaviour while pinned

- **At every wake** (a loop tick, a background task returning, a resume after
  compaction), run `bash core/scripts/hq-pin.sh check` first. Its one line is
  the frame for the tick: what is being worked toward and how many criteria
  are still open.
- **Requests that arrive mid-session** (chat, a bound DM channel, a task
  notification) are handled in service of the pin. A request outside the pin is
  done if it is small, or queued with a note under the pin if it is not; it never
  replaces the pin silently. Only the owner changes or clears a pin.
- **Progress is written down**, not remembered: `note` after each milestone,
  `done` when a criterion is met. Checkpoints and hand-offs copy the pin file
  verbatim so the next session inherits it.
- **Stopping**: the session ends its work only when `check` reports zero open
  criteria, or the owner says stop. "Nothing to do right now" means wait for
  the next signal, not finish.

## Show and check

```bash
bash core/scripts/hq-pin.sh show    # full pin: goal, owner, channel, criteria, progress
bash core/scripts/hq-pin.sh check   # one line for loop ticks; exit 3 when there is no pin
```

## Notes

- Storage is per session: `workspace/sessions/<sid>/pin.md`, plus `pin:` in the
  session's `meta.yaml` so other tooling can read the goal.
- Pairs with `/dm-bind`: bind the channel the owner reads, then post progress
  there in the same shape used for any status update.

Attribution

indigoai-usindigoai-us
View sourceMore from indigoai-us →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →