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/michael-harris/devteam/devteam-resetgit clone --depth 1 https://github.com/michael-harris/devteamWhat 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 | $0.00000 | $0.01588 |
| Opus 5 | $0.00000 | $0.00794 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
devteam-reset 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTeam Reset Command
Command: /devteam:reset [options]
Reset state, clear stuck sessions, and recover from errors.
Usage
# Abort current session and reset state
/devteam:reset
# Abort with specific reason
/devteam:reset --reason "Changing approach"
# Clear all session history (keep plans)
/devteam:reset --clear-history
# Full reset (clear everything except config)
/devteam:reset --full
# Reset specific session
/devteam:reset --session session-20260129-103045-abc123
# Dry run (show what would be reset)
/devteam:reset --dry-run
Options
| Option | Description |
|---|---|
--reason <text> |
Reason for reset (logged) |
--clear-history |
Clear all session history |
--full |
Full reset (sessions, history, temp files) |
--session <id> |
Reset specific session |
--dry-run |
Show what would be reset without doing it |
--force |
Skip confirmation prompts |
Your Process
Basic Reset (Abort Current Session)
source scripts/state.sh
source scripts/events.sh
# Check for running session
if is_session_running; then
SESSION_ID=$(get_current_session_id)
# Log the abort
log_event "session_aborted" "system" "User initiated reset" \
"{\"reason\": \"$REASON\"}"
# End session
end_session "aborted" "${REASON:-User reset}"
echo "Session $SESSION_ID aborted."
else
echo "No active session to reset."
fi
# Reset circuit breaker state
sqlite3 "$DB_FILE" "
UPDATE sessions
SET circuit_breaker_state = 'closed',
consecutive_failures = 0
WHERE status = 'running';
"
Clear History
if [[ "$CLEAR_HISTORY" == "true" ]]; then
# Confirm
if [[ "$FORCE" != "true" ]]; then
read -p "Clear all session history? This cannot be undone. [y/N] " confirm
if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
echo "Cancelled."
exit 0
fi
fi
# Clear history tables
sqlite3 "$DB_FILE" "
DELETE FROM events;
DELETE FROM agent_runs;
DELETE FROM gate_results;
DELETE FROM escalations;
DELETE FROM interviews;
DELETE FROM interview_questions;
DELETE FROM research_sessions;
DELETE FROM research_findings;
DELETE FROM sessions WHERE status != 'running';
"
echo "Session history cleared."
fi
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 · 280 lines · 0 tokens per session scan A e8ff79936236
devteam-reset is a command published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,588 tokens. 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
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
map
View, rebuild, or query the codebase dependency map.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
double-check
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.
code-explain
Explain complex code through clear narratives and visual diagrams.
health
Run documentation health checks (freshness, links, drift, cross-doc consistency).