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/execute-phasegit 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 | $0.00017 | $0.02684 |
| Opus 5 | $0.00009 | $0.01342 |
| Sonnet 5 | $0.00003 | $0.00537 |
| Haiku 4.5 | $0.00002 | $0.00268 |
Grade A, and why
gsd:execute-phase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- gsd:execute-phase — 98% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator stays lean: discover plans, analyze dependencies, group into waves, spawn subagents, collect results. Each subagent loads the full execute-plan context and handles its own plan.
Context budget: ~15% orchestrator, 100% fresh per subagent.
<execution_context> @./.claude/get-shit-done/references/ui-brand.md @./.claude/get-shit-done/workflows/execute-phase.md </execution_context>
Flags:
--gaps-only— Execute only gap closure plans (plans withgap_closure: truein frontmatter). Use after verify-work creates fix plans.
@.planning/ROADMAP.md @.planning/STATE.md
Read model profile for agent spawning:
MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
Default to "balanced" if not set.
Model lookup table:
| Agent | quality | balanced | budget |
|---|---|---|---|
| gsd-executor | opus | sonnet | sonnet |
| gsd-verifier | sonnet | sonnet | haiku |
Store resolved models for use in Task calls below.
-
Validate phase exists
- Find phase directory matching argument
- Count PLAN.md files
- Error if no plans found
-
Discover plans
- List all *-PLAN.md files in phase directory
- Check which have *-SUMMARY.md (already complete)
- If
--gaps-only: filter to only plans withgap_closure: true - Build list of incomplete plans
-
Group by wave
- Read
wavefrom each plan's frontmatter - Group plans by wave number
- Report wave structure to user
- Read
-
Execute waves For each wave in order:
- Spawn
gsd-executorfor each plan in wave (parallel Task calls) - Wait for completion (Task blocks)
- Verify SUMMARYs created
- Proceed to next wave
- Spawn
-
Aggregate results
- Collect summaries from all plans
- Report phase completion status
-
Commit any orchestrator corrections Check for uncommitted changes before verification:
git status --porcelainIf changes exist: Orchestrator made corrections between executor completions. Commit them:
git add -u && git commit -m "fix({phase}): orchestrator corrections"If clean: Continue to verification.
-
Verify phase goal Check config:
WORKFLOW_VERIFIER=$(cat .planning/config.json 2>/dev/null | grep -o '"verifier"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")If
workflow.verifierisfalse: Skip to step 8 (treat as passed).Otherwise:
- Spawn
gsd-verifiersubagent with phase directory and goal - Verifier checks must_haves against actual codebase (not SUMMARY claims)
- Creates VERIFICATION.md with detailed report
- Route by status:
passed→ continue to step 8human_needed→ present items, get approval or feedbackgaps_found→ present gaps, offer/gsd:plan-phase {X} --gaps
- Spawn
-
Update roadmap and state
- Update ROADMAP.md, STATE.md
-
Update requirements Mark phase requirements as Complete:
- Read ROADMAP.md, find this phase's
Requirements:line (e.g., "AUTH-01, AUTH-02") - Read REQUIREMENTS.md traceability table
- For each REQ-ID in this phase: change Status from "Pending" to "Complete"
- Write updated REQUIREMENTS.md
- Skip if: REQUIREMENTS.md doesn't exist, or phase has no Requirements line
- Read ROADMAP.md, find this phase's
-
Commit phase completion Check
COMMIT_PLANNING_DOCSfrom config.json (default: true). If false: Skip git operations for .planning/ files. If true: Bundle all phase metadata updates in one commit:- Stage:
git add .planning/ROADMAP.md .planning/STATE.md - Stage REQUIREMENTS.md if updated:
git add .planning/REQUIREMENTS.md - Commit:
docs({phase}): complete {phase-name} phase
- Stage:
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 · 340 lines · 17 tokens per session scan A 4c6e8be7d686
gsd:execute-phase is a command published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 25d ago), licensed MIT. It adds 17 tokens to every session and 2,684 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.