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/davidmatousek/tachi/continuegit clone --depth 1 https://github.com/davidmatousek/tachiWhat 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 | $0.00010 | $0.00613 |
| Opus 5 | $0.00005 | $0.00307 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
continue 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:
- continue — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Capture current work context and generate NEXT-SESSION.md for seamless session handoff.
File Location
| Branch Pattern | Output Location |
|---|---|
NNN-* (feature branch) |
specs/NNN-*/NEXT-SESSION.md |
| Other branches | docs/prompts/NEXT-SESSION.md |
Context to Capture
Run these git commands (in parallel):
git branch --show-current- current branchgit status --porcelain- uncommitted changesgit log -1 --format='%h %s'- last commitgit log --oneline -5- recent work
If on feature branch, also check:
- Which spec files exist (spec.md, plan.md, tasks.md)
- Task progress from tasks.md: count
[x](done) vs[ ](pending)
Phase Detection
| Files Present | Phase | Next Action |
|---|---|---|
| No spec.md | specify | Run /aod.spec |
| No plan.md | plan | Run /aod.project-plan |
| No tasks.md | tasks | Run /aod.tasks |
| All present | implement | Next pending task from tasks.md |
Output Template
# Session Continuation: {Feature Name}
**Generated**: {YYYY-MM-DD HH:MM}
**Branch**: {branch}
**Last Commit**: {hash} {message}
## Completed This Session
{List recent commits from git log}
## Current State
- **Phase**: {specify|plan|tasks|implement}
- **Uncommitted**: {file count} files ({list} or "Clean - all committed")
- **Tasks**: {X}/{Y} complete (if tasks.md exists)
## Next Actions
1. {Immediate next step based on phase}
2. {Following step}
## Context Files
{List relevant files based on phase and changes}
## Resume Command
\`\`\`bash
claude "Resume {feature} (branch: {branch}). Last: {commit summary}. Next: {action}."
\`\`\`
User Output
After writing NEXT-SESSION.md, report:
✓ Session file created: {path}
Current: {branch} | Phase: {phase} | {X} uncommitted files
Tasks: {completed}/{total} (if applicable)
Resume next session:
claude "Resume {feature}. Last: {summary}. Next: {action}."
Error Handling
| Scenario | Action |
|---|---|
| Not a git repo | ERROR: "Must be run from within a git repository" |
| Spec dir not found | Fall back to docs/prompts/NEXT-SESSION.md |
| Git commands fail | Report specific error |
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 · 93 lines · 10 tokens per session scan A 061e1a6f4b02
continue is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 10 tokens to every session and 613 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
fortigate
Run cs-security-analyst (AT + CA workflows) against the Fintech FortiGate zero-day scenario and produce a 7-task scorecard.
orchestrate
Run the full 4-agent USAP orchestration chain (cs-security-analyst → cs-incident-responder → cs-ciso-advisor → cs-security-program-manager) against the Perfect Storm scenario. Shows inter-agent handoffs and per-agent mock comparison.
README
Claude Code slash commands for the Unified Security Agent Platform (USAP). These commands let you load any USAP skill as a live LLM persona and run structured compliance tests — all inside a Claude Code session.
challenge
Run cs-security-analyst (AT workflow) against the Perfect Storm 8-vector crisis scenario and produce a 12-check mock comparison scorecard.
compare
Before/after comparison of zero-day-response SKILL.md v1 (broken) vs v2 (fixed) against the FortiGate zero-day scenario. Outputs a scored table.
run
Load a USAP skill SKILL.md and activate it as your operating persona. Argument: skill slug.