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 skills add joenandez/spectre --skill spectre-forgetgit clone --depth 1 https://github.com/joenandez/spectreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joenandez/spectre/spectre-forget)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-forget"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-forget/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-forget"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-forget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00018 | $0.00763 |
| Opus 5.5 | $0.00007 | $0.00305 |
| Sonnet 5.5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
spectre-forget 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forget
Input Handling
Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded $ARGUMENTS value.
forget: Clear Session Memory
Description
- What — Archive all session files (handoffs, todos, history) so the SessionStart hook doesn't auto-resume
- Outcome — All session files moved to archive, user informed to start fresh session
Step (1/2) - Archive Session Logs
- Action — ArchiveLogs: Move active session files for the current branch into each root's archive directory
branch=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo unknown)
canonical_dir=".spectre/handoffs/${branch}"
legacy_dir="docs/tasks/${branch}/session_logs"
archived_count=0
for session_dir in "$canonical_dir" "$legacy_dir"; do
[ -d "$session_dir" ] || continue
archive_dir="${session_dir}/archive"
while IFS= read -r -d '' session_file; do
mkdir -p "$archive_dir"
mv "$session_file" "$archive_dir/"
archived_count=$((archived_count + 1))
done < <(
find "$session_dir" -maxdepth 1 -type f \
\( -name '*_handoff.json' -o -name '*_todos.json' -o -name 'todos_history.json' \) \
-print0
)
done
if [ "$archived_count" -eq 0 ]; then
echo "NO_SESSIONS"
exit 0
fi
echo "ARCHIVED:${archived_count}"
Archive only the current branch's active, top-level files in .spectre/handoffs/{branch}/ and the matching legacy docs/tasks/{branch}/session_logs/. Do not scan another branch, descend into an existing archive/, merge the roots, or restore an archived file. The raw branch name is used directly; slash-containing branches intentionally nest.
Step (2/2) - Confirm to User
-
Action — ConfirmCleared: Based on bash output, inform user
If output is
NO_SESSIONS:No session logs found for this branch. Memory is already clear.
Else (output is
ARCHIVED:N):✓ Session memory cleared
Archived {N} session file(s) under the matching
.spectre/handoffs/{branch}/archive/and legacydocs/tasks/{branch}/session_logs/archive/directories.Next: Start a new session with
/clearor close this terminal. Your next session will start fresh without auto-loaded context.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 79 lines · 18 tokens per session scan A 6100c9a3c657
spectre-forget is a skill published in the GitHub repository joenandez/spectre (164 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 763 once invoked, about $0.0001 per session on Opus 5.5. 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.
spectre-forget compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spectre-forgetjoenandez/spectre | Skill | 164 | 1mo ago | MIT | A | 18 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |