pin

pin is a skill for Claude Code from svy04/ballast. It costs 57 tokens per session (1,134 once invoked), scanned A, original, MIT.

A skill that turns a correction or lasting working preference into a saved rule for future agent conversations. It also identifies whether the original problem was missed delivery, incomplete propagation, delegation, wording variation, or lost detail.

In plain words
What is it for?
Use it when you want the agent to remember preferences such as always doing something or avoiding a repeated mistake.
Why use it?
It prevents the same instruction from being forgotten after the current conversation. The rule is matched to future requests and can be applied across related surfaces.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the ballast plugin — 16 skills, 4 hooks shipped together

Good fit Use it when you want the agent to remember preferences such as always doing something or avoiding a repeated mistake.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/svy04/ballast/pin
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.

Any agent
npx skills add svy04/ballast --skill pin
Clone the repo
git clone --depth 1 https://github.com/svy04/ballast

Made for: Claude Code.

Or install ballast, the plugin that ships this one along with the rest of its 16 skills, 4 hooks.

Wrote 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.

agentmods badge for pin

README.md
[![agentmods](https://agentmods.dev/badge/skills/svy04/ballast/pin.svg)](https://agentmods.dev/skills/svy04/ballast/pin)
Your own site
<a href="https://agentmods.dev/skills/svy04/ballast/pin"><img src="https://agentmods.dev/badge/skills/svy04/ballast/pin.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 43
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 5.1 $0.00057 $0.01134
Opus 5 $0.00028 $0.00567
Sonnet 5 $0.00011 $0.00227
Haiku 4.5 $0.00006 $0.00113

Measured 8d ago against content hash b3d3987fd3c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pin 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 8d 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.

skills/pin/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pin — corrections become rules

A correction that lives only in the conversation dies with the conversation. Pinning it writes it into the ballast rule catalog, so the rules hook delivers it with every future message it applies to.

When the correction follows an incident, classify first

Before writing the rule, name which net failed — the remedy differs by type:

  • default regression — the rule existed but wasn't in front of the generating moment → fix delivery: keywords that will actually match future messages
  • propagation miss — one surface got fixed, its copies didn't → sweep the remaining surfaces now, then pin; when a ledger decision changed, decision-ledger's supersede sweep is the same move
  • delegation leak — the work went through a subagent or external tool the hook never reaches → the rule belongs in the brief, not only the catalog
  • variant evasion — only the literal wording was watched and a rephrasing walked through → pin patterns, not just keywords
  • compression loss — shortening or re-toning a text dropped something the text had already settled → diff the trimmed version against the one before it, part by part; a rule pinned here belongs in the editing brief, not the keyword catalog
  • substitute illusion — something adjacent to what the rule asked for got done, and that was scored as compliance → check that the artifact the rule names actually exists, rather than that the work felt covered

The last two are worth separating from the first: they happen with the rule already in view, so better delivery does not reduce them. One clause in the entry's parenthetical is enough ("propagation miss: fixed README, missed plugin.json"). An apology without a classification fixes nothing. These six types are one owner's working taxonomy, and it grew — it started at four. When an incident fits none of them, that's the next type worth naming.

Steps

  1. Extract the rule. One imperative sentence, at most two. The user's own wording beats your paraphrase. If the correction references a specific incident, keep the incident as a short parenthetical — future-you needs the why.
  2. Propose the entry in one compact block and ask nothing else:
    • id: short kebab-case
    • title: a few words — this is the label shown when the rule is injected
    • when.keywords: 4–8 keywords likely to appear in future messages where this rule matters (case-insensitive substring match) — in the language(s) the user actually types. Too-generic keywords ("please", "make") spam every turn; too-narrow ones never fire. For shapes keywords can't catch, add when.patterns (regex, case-insensitive). when.always: true fires on every message — reserve it for 1–2 rules at most.
    • body: the rule text
    • action: omit it (inject is the default) or "block" if the user wants matching requests stopped outright

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 57 tokens per session scan A b3d3987fd3c0

Subscribe to this mod's changes

pin is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 13d ago), licensed MIT. It adds 57 tokens to every session and 1,134 once invoked, about $0.0003 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

alive:save

The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…

alivecontext/alive · 78 tokens

alive:capture-context

Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…

alivecontext/alive · 74 tokens

alive:load-context

The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…

alivecontext/alive · 81 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens

alive:mine-for-context

Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…

alivecontext/alive · 63 tokens

alive:my-context-graph

Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.

alivecontext/alive · 50 tokens