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.
npx agentmods add commands/geoloeg-ist/agents-reverse-engineer/quickgit clone --depth 1 https://github.com/GeoloeG-IsT/agents-reverse-engineerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00024 | $0.01900 |
| Opus 5 | $0.00012 | $0.00950 |
| Sonnet 5 | $0.00005 | $0.00380 |
| Haiku 4.5 | $0.00002 | $0.00190 |
Grade A, and why
gsd:quick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- gsd:quick — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick mode is the same system with a shorter path:
- Spawns gsd-planner (quick mode) + gsd-executor(s)
- Skips gsd-phase-researcher, gsd-plan-checker, gsd-verifier
- Quick tasks live in
.planning/quick/separate from planned phases - Updates STATE.md "Quick Tasks Completed" table (NOT ROADMAP.md)
Use when: You know exactly what to do and the task is small enough to not need research or verification.
<execution_context> Orchestration is inline - no separate workflow file. Quick mode is deliberately simpler than full GSD. </execution_context>
Read model profile for agent spawning:
MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
Default to "balanced" if not set.
Model lookup table:
| Agent | quality | balanced | budget |
|---|---|---|---|
| gsd-planner | opus | opus | sonnet |
| gsd-executor | opus | sonnet | sonnet |
Store resolved models for use in Task calls below.
Step 1: Pre-flight validation
Check that an active GSD project exists:
if [ ! -f .planning/ROADMAP.md ]; then
echo "Quick mode requires an active project with ROADMAP.md."
echo "Run /gsd:new-project first."
exit 1
fi
If validation fails, stop immediately with the error message.
Quick tasks can run mid-phase - validation only checks ROADMAP.md exists, not phase status.
Step 2: Get task description
Prompt user interactively for the task description:
AskUserQuestion(
header: "Quick Task",
question: "What do you want to do?",
followUp: null
)
Store response as $DESCRIPTION.
If empty, re-prompt: "Please provide a task description."
Generate slug from description:
slug=$(echo "$DESCRIPTION" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | sed 's/^-//;s/-$//' | cut -c1-40)
Step 3: Calculate next quick task number
Ensure .planning/quick/ directory exists and find the next sequential number:
# Ensure .planning/quick/ exists
mkdir -p .planning/quick
# Find highest existing number and increment
last=$(ls -1d .planning/quick/[0-9][0-9][0-9]-* 2>/dev/null | sort -r | head -1 | xargs -I{} basename {} | grep -oE '^[0-9]+')
if [ -z "$last" ]; then
next_num="001"
else
next_num=$(printf "%03d" $((10#$last + 1)))
fi
Step 4: Create quick task directory
Create the directory for this quick task:
QUICK_DIR=".planning/quick/${next_num}-${slug}"
mkdir -p "$QUICK_DIR"
Report to user:
Creating quick task ${next_num}: ${DESCRIPTION}
Directory: ${QUICK_DIR}
Store $QUICK_DIR for use in orchestration.
Step 5: Spawn planner (quick mode)
Spawn gsd-planner with quick mode context:
Task(
prompt="
<planning_context>
**Mode:** quick
**Directory:** ${QUICK_DIR}
**Description:** ${DESCRIPTION}
**Project State:**
@.planning/STATE.md
</planning_context>
<constraints>
- Create a SINGLE plan with 1-3 focused tasks
- Quick tasks should be atomic and self-contained
- No research phase, no checker phase
- Target ~30% context usage (simple, focused)
</constraints>
<output>
Write plan to: ${QUICK_DIR}/${next_num}-PLAN.md
Return: ## PLANNING COMPLETE with plan path
</output>
",
subagent_type="gsd-planner",
model="{planner_model}",
description="Quick plan: ${DESCRIPTION}"
)
After planner returns:
- Verify plan exists at
${QUICK_DIR}/${next_num}-PLAN.md - Extract plan count (typically 1 for quick tasks)
- Report: "Plan created: ${QUICK_DIR}/${next_num}-PLAN.md"
If plan not found, error: "Planner failed to create ${next_num}-PLAN.md"
Step 6: Spawn executor
Spawn gsd-executor with plan reference:
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.
- 2d ago First seen · 310 lines · 24 tokens per session scan A d803955ecae2
gsd:quick is a command published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 25d ago), licensed MIT. It adds 24 tokens to every session and 1,900 once invoked, about $0.0001 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.
Other commands, from other repositories
auto-reason
Subjective self-refinement with blind judging, Borda aggregation, and provider-agnostic model routing.
deep-research
Deep research — produce a cited decision-grade research report and artifact bundle.
goals
Goal-oriented mission entrypoint — set, view, or drive long-running objectives through the mission system.
launch-worker
Manually launch headless workers against one or more GitHub issues.
check-routines
Check and safely repair aidevops routine scheduler health.
local-permissions-check
Audit local host/runtime permissions for aidevops on macOS, Linux, Windows, and WSL.