agentmods.dev

linkedin-self-improvement-loop

linkedin-self-improvement-loop is a skill for Claude Code, Codex from NachoLafuente/5050-gtm. It costs 136 tokens per session (1,558 once invoked), scanned A, original, MIT.

A measurement-and-learning loop for LinkedIn content that reads Creator analytics exports and maintains a record of beliefs about what affects reach and engagement. It proposes one experiment for the next cycle and creates drafting briefs, but does not post anything.

In plain words
What is it for?
Use it to test topics, opening lines, posting days, or post length over repeated cycles while keeping the learning history in local state files.
Why use it?
It helps you compare new results with earlier assumptions instead of treating each analytics report as a one-time snapshot.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 3repo 4mo ago A scan 136 tokens original MIT

Good fit Use it to test topics, opening lines, posting days, or post length over repeated cycles while keeping the learning history in local state files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop
View source ↗ NachoLafuente/5050-gtm
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 NachoLafuente/5050-gtm --skill linkedin-self-improvement-loop
Clone the repo
git clone --depth 1 https://github.com/NachoLafuente/5050-gtm

Made for: Claude Code, Codex.

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 linkedin-self-improvement-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop/github.svg)](https://agentmods.dev/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop)
Your own site
<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop/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.

agentmods 80×15 button for linkedin-self-improvement-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/linkedin-self-improvement-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,558 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.
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 $0.00136 $0.01558
Opus 5.5 $0.00054 $0.00623
Sonnet 5.5 $0.00027 $0.00312
Haiku 4.5 $0.00014 $0.00156

Measured 2mo ago against content hash 2da9d1c8f7ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkedin-self-improvement-loop 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (analyze.py, loop.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/linkedin-self-improvement-loop/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.

LinkedIn self-improvement loop

Most "content analytics" is a noun: a report you read once and forget. This is a verb. It runs the build-measure-learn loop on your LinkedIn and keeps state, so every cycle compounds on the last instead of starting from zero.

  1. MEASURE  -> 2. RECONCILE -> 3. UPDATE BELIEFS
  (ingest export)  (did last        (confidence rises if a
        ^           cycle's bet       pattern held, halves if
        |           hold up?)         it broke)
        |                                  |
  6. WAIT  <- 5. DRAFT BRIEFS <- 4. PROPOSE ONE EXPERIMENT
  (re-run next  (hand to a          (biggest effect on the
   export)       drafting skill)     least-settled belief)

It is advisory: it proposes experiments and emits draft briefs, but a human writes and posts every post. It never touches LinkedIn directly.

State it keeps (in --state, default ./state)

File What
beliefs.json / beliefs.md The model: ranked traits (topic/hook/day/length) with a confidence that updates each cycle. .md is git-friendly and readable.
ledger.jsonl One line per cycle: what was reconciled, discovered, proposed. The audit trail.
snapshots/<date>.json Parsed metrics from each export, so trends compute across exports (beats the top-50 survivorship trap over time).

A belief is just: "posts with this trait beat your average on the chosen metric." It starts at low confidence, climbs ~0.34 of the way to 1.0 each cycle it survives, and halves when a new export contradicts it. Survive enough cycles and it's a law; break and it's archived.

What the user downloads (same two files every cycle)

  1. Creator analytics (required) - AggregateAnalytics_<name>_<dates>.xlsx. LinkedIn -> profile -> Analytics -> Export. Impressions, engagements, top-50 posts, followers, demographics. (LinkedIn caps it at the top ~50 posts / 365 days.)
  2. Data archive (optional, recommended) - the Complete_LinkedInDataExport zip (Settings -> Data Privacy -> Get a copy of your data -> larger archive, email, ~24h). Its Shares_*.csv carries full post text so the loop can tag topics and hooks.

Read the full file on GitHub · 123 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 123 lines · 0 tokens per session scan A 2da9d1c8f7ea

Subscribe to this mod's changes

linkedin-self-improvement-loop is a skill published in the GitHub repository NachoLafuente/5050-gtm (3 stars, last pushed 4mo ago), licensed MIT. It adds 136 tokens to every session and 1,558 once invoked, about $0.0005 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 2026-08-31.

Analytics and metricsClaude CodeMarketing and SEOagent-skillsattioclaude-skillscohort-analysiscrm
Related

linkedin-self-improvement-loop compared with skills from other repositories

linkedin-self-improvement-loop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
linkedin-self-improvement-loopNachoLafuente/5050-gtmSkill34mo agoMITA136Claude Code, Codex
gt-email-infraGrowth-Today/claude-skillsSkill6yesterdayMITA232Claude Code, Codex
gt-linkedin-contentGrowth-Today/claude-skillsSkill6yesterdayMITA228Claude Code, Codex
gt-linkedin-outbounderGrowth-Today/claude-skillsSkill6yesterdayMITA236Claude Code, Codex
email-infra-bounce-auditGrowth-Today/claude-skillsSkill6yesterdayMITA157Claude Code
gt-cold-email-writerGrowth-Today/claude-skillsSkill6yesterdayMITA181Claude Code, Codex
gt-gtm-strategy-advisorGrowth-Today/claude-skillsSkill6yesterdayMITA242Claude Code, Codex