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/jinghao67/conductor/cd-bindgit clone --depth 1 https://github.com/Jinghao67/conductorWhat 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 | $0.00015 | $0.00474 |
| Opus 5 | $0.00008 | $0.00237 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
cd-bind scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Binding result (runs before you act):
!SID="${CLAUDE_SESSION_ID}"; B="$ARGUMENTS"; D=".conductor"; if [ ! -f "$D/branches/$B/brief.md" ]; then echo "No brief for $B — create it from the master with /cd-branch first."; else printf '{"session_id":"%s","role":"branch","branch_id":"%s"}\n' "$SID" "$B" > "$D/bindings/$SID.json"; tmp="$(mktemp)"; jq --arg b "$B" --arg s "$SID" '(.branches[$b].bound_session_id)=$s | (.branches[$b].status)="active"' "$D/registry.json" > "$tmp" 2>/dev/null && mv "$tmp" "$D/registry.json"; echo "bound this session to $B (role=branch)"; fi
Your brief (your ONLY context — you cannot see the master session or sibling branches):
!cat ".conductor/branches/$ARGUMENTS/brief.md" 2>/dev/null
If the binding result above did NOT print bound this session to $ARGUMENTS (e.g. it was empty or showed an error), bind manually now: write .conductor/bindings/${CLAUDE_SESSION_ID}.json with content {"session_id":"${CLAUDE_SESSION_ID}","role":"branch","branch_id":"$ARGUMENTS"}, then set .branches["$ARGUMENTS"].status to active and .bound_session_id to ${CLAUDE_SESSION_ID} in .conductor/registry.json. (This session is still unbound, so these writes are allowed.)
You are now branch $ARGUMENTS. Work directly with the user here. Reads are not firewalled in a branch — get as dirty as you need. Decisions you make are not globally binding until the master confirms them; record any cross-branch decisions to surface in your completion report. When the user confirms the work is done, run /cd-complete.
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 · 16 lines · 15 tokens per session scan A ea66abc4484d
cd-bind is a command published in the GitHub repository Jinghao67/conductor (106 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 474 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.