forbotsake-retro

A review workflow for measuring the results of published marketing content and writing a retrospective report. A retrospective is a structured review of what happened, what worked, and what should change next.

In plain words
What is it for?
Use it to review content performance, identify which approaches to continue or stop, and choose experiments for the next cycle.
Why use it?
It turns performance data into documented decisions instead of relying on memory or guesses. The supplied material indicates that it checks published logs and strategy files before producing recommendations.

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

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00099 $0.02371
Opus 5 $0.00049 $0.01185
Sonnet 5 $0.00020 $0.00474
Haiku 4.5 $0.00010 $0.00237

Measured 2d ago against content hash 27c20b534367, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forbotsake-retro scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

echo "WARNING: forbotsake not found. Install: bash <(curl -fsSL https://raw.githubusercontent.com/forbotsake/forbotsake/main/bin/install.sh)"
.agents/skills/forbotsake-retro/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forbotsake-retro

Measure. Learn. Decide. The feedback loop that makes marketing compound.

Preamble

FORBOTSAKE_HOME="${FORBOTSAKE_HOME:-$HOME/.forbotsake}"
mkdir -p "$FORBOTSAKE_HOME"

# Discover forbotsake install directory
_FBS_ROOT=""
for _FBS_CANDIDATE in "$HOME/.codex/skills/forbotsake" "$HOME/.agents/skills/forbotsake"; do
  [ -d "$_FBS_CANDIDATE" ] && _FBS_ROOT="$_FBS_CANDIDATE" && break
done
if [ -z "$_FBS_ROOT" ]; then
  echo "WARNING: forbotsake not found. Install: bash <(curl -fsSL https://raw.githubusercontent.com/forbotsake/forbotsake/main/bin/install.sh)"
fi

# Check for updates
_UPD=""
[ -n "$_FBS_ROOT" ] && [ -x "$_FBS_ROOT/bin/forbotsake-update-check" ] && _UPD=$("$_FBS_ROOT/bin/forbotsake-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "BRANCH: $_BRANCH"

# Check for published log
if [ -f published-log.md ]; then
  echo "PUBLISHED_LOG: yes"
  wc -l published-log.md
else
  echo "PUBLISHED_LOG: no"
fi

# Check for strategy.md
if [ -f strategy.md ]; then
  echo "STRATEGY: yes"
else
  echo "STRATEGY: no"
fi

# Check for existing retro reports
if [ -d retros/ ]; then
  echo "RETRO_DIR: yes"
  ls -1 retros/ 2>/dev/null | tail -5
else
  echo "RETRO_DIR: no"
fi

If output shows UPGRADE_AVAILABLE <old> <new>: read the forbotsake-upgrade SKILL.md at $_FBS_ROOT/forbotsake-upgrade/SKILL.md (where _FBS_ROOT is the variable already resolved in the preamble bash above) and follow the "Inline upgrade flow" section Step 1 only. If Step 1 results in "Yes" or "Always" (proceed with upgrade), continue through Steps 2-7 of the inline flow. If Step 1 results in "Not now" or "Never" (declined), skip Steps 2-7 entirely and continue with this skill immediately.

If output shows JUST_UPGRADED <old> <new>: tell user "Running forbotsake v{new} (just updated from v{old})!" and continue.

If PUBLISHED_LOG is no: "No published-log.md found. I need to know what you published to analyze results. Either run /forbotsake-publish to ship content (it logs automatically), or tell me what you published and I'll work from that." Ask the user directly in conversation to let the user provide publishing history manually.

Read the full file on GitHub · 295 lines

Files

What ships with it

1 file 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. 2d ago First seen · 295 lines · 99 tokens per session scan A 27c20b534367

Subscribe to this mod's changes

forbotsake-retro is a skill published in the GitHub repository forbotsake/forbotsake (5 stars, last pushed 16d ago), licensed MIT. It adds 99 tokens to every session and 2,371 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

account-health

Score a customer's health, start the renewal motion, and flag churn or expansion early. Trigger when the user asks "how's this account doing", "health check", "are we at risk of churn", "is this account ready to expand", or before a renewal or QBR.

etrebels/claude-code-growth-os · 60 tokens

churn-save

Turn a red/amber account into a recovery play — the real risk, the re-engagement outreach, the renewal-clock timing. Trigger when account-health flags a 🔴/🟡 account, when the user says "save this account", "they're going to churn", "the customer went quiet", "renewal at risk", or right after a RETENTION-RISK line is…

etrebels/claude-code-growth-os · 84 tokens

expansion-signal

Work an expansion-ready account into an angle and a clean hand to sales — the second growth motion the funnel forgets. Trigger when account-health flags an EXPANSION-SIGNAL, when a healthy account asks for more unprompted, a second team wants access, or the user says "this account is ready to grow", "expansion play"…

etrebels/claude-code-growth-os · 85 tokens

product-signal

Route post-sale and field signals into product's roadmap queue, and write the buyer-facing line for anything shipped. Trigger when the user says "what should product hear", "triage the roadmap signals", "route this to product", "feature request", or "what does this feature mean for the buyer".

etrebels/claude-code-growth-os · 65 tokens

retention-feedback

Turn what customer success hears after the sale into product and retention actions. Trigger when an onboarding note, QBR, support thread, or usage review surfaces adoption friction, a churn-risk signal, a feature request that blocks expansion, or a customer who's ready to grow — or when the user says "log this for…

etrebels/claude-code-growth-os · 86 tokens

event-to-pipeline

Turn a conference, meetup, or event you attend or host into booked calls. Trigger when the user is about to attend or host an event, asks how to "work the room", or names an upcoming conference/meetup.

etrebels/claude-code-growth-os · 51 tokens