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/icloudza/algokiller-plugin/rebindgit clone --depth 1 https://github.com/icloudza/algokiller-pluginWhat 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 | $0.00042 | $0.00326 |
| Opus 5 | $0.00021 | $0.00163 |
| Sonnet 5 | $0.00008 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
rebind 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
The user wants a clean session on the same trace they were just analysing.
Steps:
-
Recover the current binding. The previous
bind_traceresponse should still be in your context — extracttrace_file,mode, andoutput_dir_resolved. If you don't have them, ask the user for the trace path; do NOT guess. -
Re-invoke
bind_tracewith those exact values plusoutput_dirset to the parent of the previousoutput_dir_resolvedso the new resolution lands in the SAME project's.algokiller/<trace>/<NEW_TIMESTAMP>/rather than rolling Documents fallback.Example: previous
output_dir_resolvedwas/Users/foo/proj/.algokiller/login.trace/20990101_120000— passoutput_dir = /Users/foo/proj/.algokiller/login.trace(the parent of the old timestamp dir) so the resolver creates a fresh<NEW_TIMESTAMP>/under it. -
Report the new session directory to the user verbatim, in one short sentence.
DO NOT carry hypotheses across — the new session has a fresh ledger by design (each bind == fresh ledger; see CHANGELOG 0.9.6). If the user wants continuity, they should explicitly say so and you'd re-add hypotheses manually.
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 · 20 lines · 42 tokens per session scan A 62c3dac84375
rebind is a command published in the GitHub repository icloudza/algokiller-plugin (77 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 326 once invoked, about $0.0002 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
workflow-foundation-sprint
Run the Foundation Sprint workflow (2-day strategic-alignment arc producing a Founding Hypothesis).
workflow-foundation-to-design
Run the end-to-end Foundation Sprint + Design Sprint workflow with narrative handoff.
workflow-technical-discovery
Run the Technical Discovery workflow (spike -> ADR -> design rationale).
memcord-save-progress
Auto-summarize and save conversation progress.
memcord-unbind
Remove .memcord binding from a project directory.
enrich
Enrich project memory by mining 100 recently merged PRs: extracts decisions, conventions, gotchas, and architectural facts from PR discussions, review comments, and PR bodies.